TaherFattahi's picture
init: tetris neural network model with q learning
03b0d13
Average reward over those 100 experiences on model w/ 0 trained experiences: -0.27
Average reward over those 100 experiences on model w/ 100 trained experiences: 0.27
Average reward over those 100 experiences on model w/ 200 trained experiences: -0.21
Average reward over those 100 experiences on model w/ 300 trained experiences: -0.28
Average reward over those 100 experiences on model w/ 400 trained experiences: 0.15
Average reward over those 100 experiences on model w/ 500 trained experiences: 0.14
Average reward over those 100 experiences on model w/ 600 trained experiences: 0.43
Average reward over those 100 experiences on model w/ 700 trained experiences: 0.22
Average reward over those 100 experiences on model w/ 800 trained experiences: 0.16
Average reward over those 100 experiences on model w/ 900 trained experiences: 0.46
Average reward over those 100 experiences on model w/ 1000 trained experiences: 0.4
Average reward over those 100 experiences on model w/ 1100 trained experiences: 0.3
Average reward over those 100 experiences on model w/ 1200 trained experiences: 0.47
Average reward over those 100 experiences on model w/ 1300 trained experiences: 0.4
Average reward over those 100 experiences on model w/ 1400 trained experiences: 0.37
Average reward over those 100 experiences on model w/ 1500 trained experiences: 0.46
Average reward over those 100 experiences on model w/ 1600 trained experiences: 0.74
Average reward over those 100 experiences on model w/ 1700 trained experiences: 0.29
Average reward over those 100 experiences on model w/ 1800 trained experiences: 0.76
Average reward over those 100 experiences on model w/ 1900 trained experiences: 0.51
Average reward over those 100 experiences on model w/ 2000 trained experiences: 0.49
Average reward over those 100 experiences on model w/ 2100 trained experiences: 0.66
Average reward over those 100 experiences on model w/ 2200 trained experiences: 0.68
Average reward over those 100 experiences on model w/ 2300 trained experiences: 0.81
Average reward over those 100 experiences on model w/ 2400 trained experiences: 0.4
Average reward over those 100 experiences on model w/ 2500 trained experiences: 0.41
Average reward over those 100 experiences on model w/ 2600 trained experiences: 0.52
Average reward over those 100 experiences on model w/ 2700 trained experiences: 0.45
Average reward over those 100 experiences on model w/ 2800 trained experiences: 0.61
Average reward over those 100 experiences on model w/ 2900 trained experiences: 0.5
Average reward over those 100 experiences on model w/ 3000 trained experiences: 0.6
Average reward over those 100 experiences on model w/ 3100 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 3200 trained experiences: 0.28
Average reward over those 100 experiences on model w/ 3300 trained experiences: 0.73
Average reward over those 100 experiences on model w/ 3400 trained experiences: 0.61
Average reward over those 100 experiences on model w/ 3500 trained experiences: 0.59
Average reward over those 100 experiences on model w/ 3600 trained experiences: 0.45
Average reward over those 100 experiences on model w/ 3700 trained experiences: 0.61
Average reward over those 100 experiences on model w/ 3800 trained experiences: 0.47
Average reward over those 100 experiences on model w/ 3900 trained experiences: 0.7
Average reward over those 100 experiences on model w/ 4000 trained experiences: 0.82
Average reward over those 100 experiences on model w/ 4100 trained experiences: 0.68
Average reward over those 100 experiences on model w/ 4200 trained experiences: 0.65
Average reward over those 100 experiences on model w/ 4300 trained experiences: 0.7
Average reward over those 100 experiences on model w/ 4400 trained experiences: 0.67
Average reward over those 100 experiences on model w/ 4500 trained experiences: 0.71
Average reward over those 100 experiences on model w/ 4600 trained experiences: 0.92
Average reward over those 100 experiences on model w/ 4700 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 4800 trained experiences: 0.69
Average reward over those 100 experiences on model w/ 4900 trained experiences: 0.67
Average reward over those 100 experiences on model w/ 0 trained experiences: -0.2
Average reward over those 100 experiences on model w/ 100 trained experiences: 0.03
Average reward over those 100 experiences on model w/ 200 trained experiences: 0.31
Average reward over those 100 experiences on model w/ 300 trained experiences: -0.25
Average reward over those 100 experiences on model w/ 400 trained experiences: -0.27
Average reward over those 100 experiences on model w/ 500 trained experiences: 0.52
Average reward over those 100 experiences on model w/ 600 trained experiences: 0.39
Average reward over those 100 experiences on model w/ 700 trained experiences: 0.24
Average reward over those 100 experiences on model w/ 800 trained experiences: 0.58
Average reward over those 100 experiences on model w/ 900 trained experiences: 0.42
Average reward over those 100 experiences on model w/ 1000 trained experiences: 0.23
Average reward over those 100 experiences on model w/ 1100 trained experiences: 0.51
Average reward over those 100 experiences on model w/ 1200 trained experiences: 0.26
Average reward over those 100 experiences on model w/ 1300 trained experiences: 0.1
Average reward over those 100 experiences on model w/ 1400 trained experiences: 0.81
Average reward over those 100 experiences on model w/ 1500 trained experiences: 0.15
Average reward over those 100 experiences on model w/ 1600 trained experiences: 0.56
Average reward over those 100 experiences on model w/ 1700 trained experiences: 0.22
Average reward over those 100 experiences on model w/ 1800 trained experiences: 0.35
Average reward over those 100 experiences on model w/ 1900 trained experiences: 0.61
Average reward over those 100 experiences on model w/ 2000 trained experiences: 0.6
Average reward over those 100 experiences on model w/ 2100 trained experiences: 0.47
Average reward over those 100 experiences on model w/ 2200 trained experiences: 0.58
Average reward over those 100 experiences on model w/ 2300 trained experiences: 0.25
Average reward over those 100 experiences on model w/ 2400 trained experiences: 0.45
Average reward over those 100 experiences on model w/ 2500 trained experiences: 0.31
Average reward over those 100 experiences on model w/ 2600 trained experiences: 0.57
Average reward over those 100 experiences on model w/ 2700 trained experiences: 0.44
Average reward over those 100 experiences on model w/ 2800 trained experiences: 0.42
Average reward over those 100 experiences on model w/ 2900 trained experiences: 0.49
Average reward over those 100 experiences on model w/ 3000 trained experiences: 0.65
Average reward over those 100 experiences on model w/ 3100 trained experiences: 0.61
Average reward over those 100 experiences on model w/ 3200 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 3300 trained experiences: 0.65
Average reward over those 100 experiences on model w/ 3400 trained experiences: 0.47
Average reward over those 100 experiences on model w/ 3500 trained experiences: 0.46
Average reward over those 100 experiences on model w/ 3600 trained experiences: 0.48
Average reward over those 100 experiences on model w/ 3700 trained experiences: 0.74
Average reward over those 100 experiences on model w/ 3800 trained experiences: 0.23
Average reward over those 100 experiences on model w/ 3900 trained experiences: 0.65
Average reward over those 100 experiences on model w/ 4000 trained experiences: 0.7
Average reward over those 100 experiences on model w/ 4100 trained experiences: 0.42
Average reward over those 100 experiences on model w/ 4200 trained experiences: 0.81
Average reward over those 100 experiences on model w/ 4300 trained experiences: 0.56
Average reward over those 100 experiences on model w/ 4400 trained experiences: 0.45
Average reward over those 100 experiences on model w/ 4500 trained experiences: 0.82
Average reward over those 100 experiences on model w/ 4600 trained experiences: 0.37
Average reward over those 100 experiences on model w/ 4700 trained experiences: 0.52
Average reward over those 100 experiences on model w/ 4800 trained experiences: 0.62
Average reward over those 100 experiences on model w/ 4900 trained experiences: 0.51
Average reward over those 100 experiences on model w/ 0 trained experiences: -0.25
Average reward over those 100 experiences on model w/ 100 trained experiences: 0.12
Average reward over those 100 experiences on model w/ 200 trained experiences: 0.25
Average reward over those 100 experiences on model w/ 300 trained experiences: 0.43
Average reward over those 100 experiences on model w/ 400 trained experiences: 0.46
Average reward over those 100 experiences on model w/ 500 trained experiences: 0.57
Average reward over those 100 experiences on model w/ 600 trained experiences: -0.08
Average reward over those 100 experiences on model w/ 700 trained experiences: -0.11
Average reward over those 100 experiences on model w/ 800 trained experiences: 0.38
Average reward over those 100 experiences on model w/ 900 trained experiences: 0.21
Average reward over those 100 experiences on model w/ 1000 trained experiences: 0.5
Average reward over those 100 experiences on model w/ 1100 trained experiences: 0.35
Average reward over those 100 experiences on model w/ 1200 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 1300 trained experiences: 0.55
Average reward over those 100 experiences on model w/ 1400 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 1500 trained experiences: 0.47
Average reward over those 100 experiences on model w/ 1600 trained experiences: 0.73
Average reward over those 100 experiences on model w/ 1700 trained experiences: 0.24
Average reward over those 100 experiences on model w/ 1800 trained experiences: 0.61
Average reward over those 100 experiences on model w/ 1900 trained experiences: 0.46
Average reward over those 100 experiences on model w/ 2000 trained experiences: 0.81
Average reward over those 100 experiences on model w/ 2100 trained experiences: 0.43
Average reward over those 100 experiences on model w/ 2200 trained experiences: 0.78
Average reward over those 100 experiences on model w/ 2300 trained experiences: 0.53
Average reward over those 100 experiences on model w/ 2400 trained experiences: 0.53
Average reward over those 100 experiences on model w/ 2500 trained experiences: 0.21
Average reward over those 100 experiences on model w/ 2600 trained experiences: 0.52
Average reward over those 100 experiences on model w/ 2700 trained experiences: 0.41
Average reward over those 100 experiences on model w/ 2800 trained experiences: 0.75
Average reward over those 100 experiences on model w/ 2900 trained experiences: 0.64
Average reward over those 100 experiences on model w/ 3000 trained experiences: 0.64
Average reward over those 100 experiences on model w/ 3100 trained experiences: 0.05
Average reward over those 100 experiences on model w/ 3200 trained experiences: 0.45
Average reward over those 100 experiences on model w/ 3300 trained experiences: 0.75
Average reward over those 100 experiences on model w/ 3400 trained experiences: 0.72
Average reward over those 100 experiences on model w/ 3500 trained experiences: 0.41
Average reward over those 100 experiences on model w/ 3600 trained experiences: 0.64
Average reward over those 100 experiences on model w/ 3700 trained experiences: 0.55
Average reward over those 100 experiences on model w/ 3800 trained experiences: 0.51
Average reward over those 100 experiences on model w/ 3900 trained experiences: 0.58
Average reward over those 100 experiences on model w/ 4000 trained experiences: 0.42
Average reward over those 100 experiences on model w/ 4100 trained experiences: 0.82
Average reward over those 100 experiences on model w/ 4200 trained experiences: 0.87
Average reward over those 100 experiences on model w/ 4300 trained experiences: 0.45
Average reward over those 100 experiences on model w/ 4400 trained experiences: 0.7
Average reward over those 100 experiences on model w/ 4500 trained experiences: 0.46
Average reward over those 100 experiences on model w/ 4600 trained experiences: 0.67
Average reward over those 100 experiences on model w/ 4700 trained experiences: 0.61
Average reward over those 100 experiences on model w/ 4800 trained experiences: 0.44
Average reward over those 100 experiences on model w/ 4900 trained experiences: 0.86
Average reward over those 100 experiences on model w/ 0 trained experiences: -0.04
Average reward over those 100 experiences on model w/ 100 trained experiences: -0.27
Average reward over those 100 experiences on model w/ 200 trained experiences: -0.28
Average reward over those 100 experiences on model w/ 300 trained experiences: 0.3
Average reward over those 100 experiences on model w/ 400 trained experiences: 0.57
Average reward over those 100 experiences on model w/ 500 trained experiences: 0.13
Average reward over those 100 experiences on model w/ 600 trained experiences: 0.16
Average reward over those 100 experiences on model w/ 700 trained experiences: 0.54
Average reward over those 100 experiences on model w/ 800 trained experiences: 0.17
Average reward over those 100 experiences on model w/ 900 trained experiences: 0.13
Average reward over those 100 experiences on model w/ 1000 trained experiences: 0.37
Average reward over those 100 experiences on model w/ 1100 trained experiences: 0.41
Average reward over those 100 experiences on model w/ 1200 trained experiences: 0.49
Average reward over those 100 experiences on model w/ 1300 trained experiences: 0.52
Average reward over those 100 experiences on model w/ 1400 trained experiences: 0.68
Average reward over those 100 experiences on model w/ 1500 trained experiences: 0.59
Average reward over those 100 experiences on model w/ 1600 trained experiences: 0.23
Average reward over those 100 experiences on model w/ 1700 trained experiences: 0.41
Average reward over those 100 experiences on model w/ 1800 trained experiences: -0.18
Average reward over those 100 experiences on model w/ 1900 trained experiences: 0.82
Average reward over those 100 experiences on model w/ 2000 trained experiences: 0.5
Average reward over those 100 experiences on model w/ 2100 trained experiences: 0.33
Average reward over those 100 experiences on model w/ 2200 trained experiences: 0.3
Average reward over those 100 experiences on model w/ 2300 trained experiences: 0.33
Average reward over those 100 experiences on model w/ 2400 trained experiences: 0.5
Average reward over those 100 experiences on model w/ 2500 trained experiences: 0.72
Average reward over those 100 experiences on model w/ 2600 trained experiences: 0.51
Average reward over those 100 experiences on model w/ 2700 trained experiences: 0.42
Average reward over those 100 experiences on model w/ 2800 trained experiences: 0.58
Average reward over those 100 experiences on model w/ 2900 trained experiences: 0.47
Average reward over those 100 experiences on model w/ 3000 trained experiences: 0.67
Average reward over those 100 experiences on model w/ 3100 trained experiences: 0.45
Average reward over those 100 experiences on model w/ 3200 trained experiences: 0.87
Average reward over those 100 experiences on model w/ 3300 trained experiences: 0.56
Average reward over those 100 experiences on model w/ 3400 trained experiences: 0.73
Average reward over those 100 experiences on model w/ 3500 trained experiences: 0.87
Average reward over those 100 experiences on model w/ 3600 trained experiences: 0.55
Average reward over those 100 experiences on model w/ 3700 trained experiences: 0.53
Average reward over those 100 experiences on model w/ 3800 trained experiences: 0.81
Average reward over those 100 experiences on model w/ 3900 trained experiences: 0.55
Average reward over those 100 experiences on model w/ 4000 trained experiences: 0.58
Average reward over those 100 experiences on model w/ 4100 trained experiences: 0.72
Average reward over those 100 experiences on model w/ 4200 trained experiences: 0.81
Average reward over those 100 experiences on model w/ 4300 trained experiences: 0.61
Average reward over those 100 experiences on model w/ 4400 trained experiences: 0.63
Average reward over those 100 experiences on model w/ 4500 trained experiences: 0.73
Average reward over those 100 experiences on model w/ 4600 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 4700 trained experiences: 0.82
Average reward over those 100 experiences on model w/ 4800 trained experiences: 0.81
Average reward over those 100 experiences on model w/ 4900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 0 trained experiences: -0.19
Average reward over those 100 experiences on model w/ 100 trained experiences: 0.28
Average reward over those 100 experiences on model w/ 200 trained experiences: -0.16
Average reward over those 100 experiences on model w/ 300 trained experiences: 0.28
Average reward over those 100 experiences on model w/ 400 trained experiences: 0.36
Average reward over those 100 experiences on model w/ 500 trained experiences: 0.07
Average reward over those 100 experiences on model w/ 600 trained experiences: 0.24
Average reward over those 100 experiences on model w/ 700 trained experiences: 0.42
Average reward over those 100 experiences on model w/ 800 trained experiences: 0.22
Average reward over those 100 experiences on model w/ 900 trained experiences: 0.3
Average reward over those 100 experiences on model w/ 1000 trained experiences: 0.24
Average reward over those 100 experiences on model w/ 1100 trained experiences: 0.33
Average reward over those 100 experiences on model w/ 1200 trained experiences: 0.66
Average reward over those 100 experiences on model w/ 1300 trained experiences: 0.14
Average reward over those 100 experiences on model w/ 1400 trained experiences: 0.46
Average reward over those 100 experiences on model w/ 1500 trained experiences: 0.55
Average reward over those 100 experiences on model w/ 1600 trained experiences: 0.53
Average reward over those 100 experiences on model w/ 1700 trained experiences: 0.35
Average reward over those 100 experiences on model w/ 1800 trained experiences: 0.3
Average reward over those 100 experiences on model w/ 1900 trained experiences: 0.57
Average reward over those 100 experiences on model w/ 2000 trained experiences: 0.48
Average reward over those 100 experiences on model w/ 2100 trained experiences: 0.47
Average reward over those 100 experiences on model w/ 2200 trained experiences: 0.51
Average reward over those 100 experiences on model w/ 2300 trained experiences: 0.5
Average reward over those 100 experiences on model w/ 2400 trained experiences: 0.48
Average reward over those 100 experiences on model w/ 2500 trained experiences: 0.39
Average reward over those 100 experiences on model w/ 2600 trained experiences: 0.54
Average reward over those 100 experiences on model w/ 2700 trained experiences: 0.69
Average reward over those 100 experiences on model w/ 2800 trained experiences: 0.45
Average reward over those 100 experiences on model w/ 2900 trained experiences: 0.63
Average reward over those 100 experiences on model w/ 3000 trained experiences: 0.53
Average reward over those 100 experiences on model w/ 3100 trained experiences: 0.54
Average reward over those 100 experiences on model w/ 3200 trained experiences: 0.46
Average reward over those 100 experiences on model w/ 3300 trained experiences: 0.57
Average reward over those 100 experiences on model w/ 3400 trained experiences: 0.67
Average reward over those 100 experiences on model w/ 3500 trained experiences: 0.58
Average reward over those 100 experiences on model w/ 3600 trained experiences: 0.61
Average reward over those 100 experiences on model w/ 3700 trained experiences: 0.69
Average reward over those 100 experiences on model w/ 3800 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 3900 trained experiences: 0.78
Average reward over those 100 experiences on model w/ 4000 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 4100 trained experiences: 0.66
Average reward over those 100 experiences on model w/ 4200 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 4300 trained experiences: 0.87
Average reward over those 100 experiences on model w/ 4400 trained experiences: 0.82
Average reward over those 100 experiences on model w/ 4500 trained experiences: 0.77
Average reward over those 100 experiences on model w/ 4600 trained experiences: 0.66
Average reward over those 100 experiences on model w/ 4700 trained experiences: 0.68
Average reward over those 100 experiences on model w/ 4800 trained experiences: 0.59
Average reward over those 100 experiences on model w/ 4900 trained experiences: 0.67
Average reward over those 100 experiences on model w/ 5000 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 5100 trained experiences: 0.86
Average reward over those 100 experiences on model w/ 5200 trained experiences: 0.66
Average reward over those 100 experiences on model w/ 5300 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 5400 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 5500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 5600 trained experiences: 0.74
Average reward over those 100 experiences on model w/ 5700 trained experiences: 0.61
Average reward over those 100 experiences on model w/ 5800 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 5900 trained experiences: 0.63
Average reward over those 100 experiences on model w/ 6000 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 6100 trained experiences: 0.82
Average reward over those 100 experiences on model w/ 6200 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 6300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 6400 trained experiences: 0.63
Average reward over those 100 experiences on model w/ 6500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 6600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 6700 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 6800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 6900 trained experiences: 0.92
Average reward over those 100 experiences on model w/ 7000 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 7100 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 7200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 7300 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 7400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 7500 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 7600 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 7700 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 7800 trained experiences: 0.69
Average reward over those 100 experiences on model w/ 7900 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 8000 trained experiences: 0.57
Average reward over those 100 experiences on model w/ 8100 trained experiences: 0.63
Average reward over those 100 experiences on model w/ 8200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 8300 trained experiences: 0.65
Average reward over those 100 experiences on model w/ 8400 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 8500 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 8600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 8700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 8800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 8900 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 9000 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 9100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 9200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 9300 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 9400 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 9500 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 9600 trained experiences: 0.75
Average reward over those 100 experiences on model w/ 9700 trained experiences: 0.69
Average reward over those 100 experiences on model w/ 9800 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 9900 trained experiences: 0.62
Average reward over those 100 experiences on model w/ 10000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 10100 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 10200 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 10300 trained experiences: 0.57
Average reward over those 100 experiences on model w/ 10400 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 10500 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 10600 trained experiences: 0.74
Average reward over those 100 experiences on model w/ 10700 trained experiences: 0.7
Average reward over those 100 experiences on model w/ 10800 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 10900 trained experiences: 0.75
Average reward over those 100 experiences on model w/ 11000 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 11100 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 11200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 11300 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 11400 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 11500 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 11600 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 11700 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 11800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 11900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 12000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 12100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 12200 trained experiences: 0.82
Average reward over those 100 experiences on model w/ 12300 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 12400 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 12500 trained experiences: 0.68
Average reward over those 100 experiences on model w/ 12600 trained experiences: 0.69
Average reward over those 100 experiences on model w/ 12700 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 12800 trained experiences: 0.82
Average reward over those 100 experiences on model w/ 12900 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 13000 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 13100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 13200 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 13300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 13400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 13500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 13600 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 13700 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 13800 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 13900 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 14000 trained experiences: 0.77
Average reward over those 100 experiences on model w/ 14100 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 14200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 14300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 14400 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 14500 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 14600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 14700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 14800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 14900 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 15000 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 15100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 15200 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 15300 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 15400 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 15500 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 15600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 15700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 15800 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 15900 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 16000 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 16100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 16200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 16300 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 16400 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 16500 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 16600 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 16700 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 16800 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 16900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 17000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 17100 trained experiences: 0.82
Average reward over those 100 experiences on model w/ 17200 trained experiences: 0.45
Average reward over those 100 experiences on model w/ 17300 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 17400 trained experiences: 0.68
Average reward over those 100 experiences on model w/ 17500 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 17600 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 17700 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 17800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 17900 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 18000 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 18100 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 18200 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 18300 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 18400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 18500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 18600 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 18700 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 18800 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 18900 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 19000 trained experiences: 0.69
Average reward over those 100 experiences on model w/ 19100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 19200 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 19300 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 19400 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 19500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 19600 trained experiences: 0.71
Average reward over those 100 experiences on model w/ 19700 trained experiences: 0.86
Average reward over those 100 experiences on model w/ 19800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 19900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 20000 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 20100 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 20200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 20300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 20400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 20500 trained experiences: 0.68
Average reward over those 100 experiences on model w/ 20600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 20700 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 20800 trained experiences: 0.82
Average reward over those 100 experiences on model w/ 20900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 21000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 21100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 21200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 21300 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 21400 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 21500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 21600 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 21700 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 21800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 21900 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 22000 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 22100 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 22200 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 22300 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 22400 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 22500 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 22600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 22700 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 22800 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 22900 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 23000 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 23100 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 23200 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 23300 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 23400 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 23500 trained experiences: 0.82
Average reward over those 100 experiences on model w/ 23600 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 23700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 23800 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 23900 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 24000 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 24100 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 24200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 24300 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 24400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 24500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 24600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 24700 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 24800 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 24900 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 25000 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 25100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 25200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 25300 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 25400 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 25500 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 25600 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 25700 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 25800 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 25900 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 26000 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 26100 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 26200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 26300 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 26400 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 26500 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 26600 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 26700 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 26800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 26900 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 27000 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 27100 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 27200 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 27300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 27400 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 27500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 27600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 27700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 27800 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 27900 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 28000 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 28100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 28200 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 28300 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 28400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 28500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 28600 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 28700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 28800 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 28900 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 29000 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 29100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 29200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 29300 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 29400 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 29500 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 29600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 29700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 29800 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 29900 trained experiences: 0.82
Average reward over those 100 experiences on model w/ 30000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 30100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 30200 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 30300 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 30400 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 30500 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 30600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 30700 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 30800 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 30900 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 31000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 31100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 31200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 31300 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 31400 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 31500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 31600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 31700 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 31800 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 31900 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 32000 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 32100 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 32200 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 32300 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 32400 trained experiences: 0.74
Average reward over those 100 experiences on model w/ 32500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 32600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 32700 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 32800 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 32900 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 33000 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 33100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 33200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 33300 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 33400 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 33500 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 33600 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 33700 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 33800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 33900 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 34000 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 34100 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 34200 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 34300 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 34400 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 34500 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 34600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 34700 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 34800 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 34900 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 35000 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 35100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 35200 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 35300 trained experiences: 0.78
Average reward over those 100 experiences on model w/ 35400 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 35500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 35600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 35700 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 35800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 35900 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 36000 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 36100 trained experiences: 0.78
Average reward over those 100 experiences on model w/ 36200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 36300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 36400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 36500 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 36600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 36700 trained experiences: 0.75
Average reward over those 100 experiences on model w/ 36800 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 36900 trained experiences: 0.75
Average reward over those 100 experiences on model w/ 37000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 37100 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 37200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 37300 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 37400 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 37500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 37600 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 37700 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 37800 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 37900 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 38000 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 38100 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 38200 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 38300 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 38400 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 38500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 38600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 38700 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 38800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 38900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 39000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 39100 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 39200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 39300 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 39400 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 39500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 39600 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 39700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 39800 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 39900 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 40000 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 40100 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 40200 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 40300 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 40400 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 40500 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 40600 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 40700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 40800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 40900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 41000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 41100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 41200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 41300 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 41400 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 41500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 41600 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 41700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 41800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 41900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 42000 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 42100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 42200 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 42300 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 42400 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 42500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 42600 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 42700 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 42800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 42900 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 43000 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 43100 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 43200 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 43300 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 43400 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 43500 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 43600 trained experiences: 0.74
Average reward over those 100 experiences on model w/ 43700 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 43800 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 43900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 44000 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 44100 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 44200 trained experiences: 0.78
Average reward over those 100 experiences on model w/ 44300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 44400 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 44500 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 44600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 44700 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 44800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 44900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 45000 trained experiences: 0.78
Average reward over those 100 experiences on model w/ 45100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 45200 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 45300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 45400 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 45500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 45600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 45700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 45800 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 45900 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 46000 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 46100 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 46200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 46300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 46400 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 46500 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 46600 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 46700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 46800 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 46900 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 47000 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 47100 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 47200 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 47300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 47400 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 47500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 47600 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 47700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 47800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 47900 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 48000 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 48100 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 48200 trained experiences: 0.73
Average reward over those 100 experiences on model w/ 48300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 48400 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 48500 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 48600 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 48700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 48800 trained experiences: 0.78
Average reward over those 100 experiences on model w/ 48900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 49000 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 49100 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 49200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 49300 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 49400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 49500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 49600 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 49700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 49800 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 49900 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 50000 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 50100 trained experiences: 0.72
Average reward over those 100 experiences on model w/ 50200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 50300 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 50400 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 50500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 50600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 50700 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 50800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 50900 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 51000 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 51100 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 51200 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 51300 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 51400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 51500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 51600 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 51700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 51800 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 51900 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 52000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 52100 trained experiences: 0.92
Average reward over those 100 experiences on model w/ 52200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 52300 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 52400 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 52500 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 52600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 52700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 52800 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 52900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 53000 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 53100 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 53200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 53300 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 53400 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 53500 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 53600 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 53700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 53800 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 53900 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 54000 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 54100 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 54200 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 54300 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 54400 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 54500 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 54600 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 54700 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 54800 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 54900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 55000 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 55100 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 55200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 55300 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 55400 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 55500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 55600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 55700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 55800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 55900 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 56000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 56100 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 56200 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 56300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 56400 trained experiences: 0.87
Average reward over those 100 experiences on model w/ 56500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 56600 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 56700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 56800 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 56900 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 57000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 57100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 57200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 57300 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 57400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 57500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 57600 trained experiences: 0.87
Average reward over those 100 experiences on model w/ 57700 trained experiences: 0.78
Average reward over those 100 experiences on model w/ 57800 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 57900 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 58000 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 58100 trained experiences: 0.87
Average reward over those 100 experiences on model w/ 58200 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 58300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 58400 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 58500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 58600 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 58700 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 58800 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 58900 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 59000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 59100 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 59200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 59300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 59400 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 59500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 59600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 59700 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 0 trained experiences: -0.33
Average reward over those 100 experiences on model w/ 100 trained experiences: 0.24
Average reward over those 100 experiences on model w/ 200 trained experiences: -0.33
Average reward over those 100 experiences on model w/ 300 trained experiences: 0.33
Average reward over those 100 experiences on model w/ 400 trained experiences: -0.17
Average reward over those 100 experiences on model w/ 500 trained experiences: 0.47
Average reward over those 100 experiences on model w/ 600 trained experiences: -0.1
Average reward over those 100 experiences on model w/ 700 trained experiences: 0.34
Average reward over those 100 experiences on model w/ 800 trained experiences: 0.61
Average reward over those 100 experiences on model w/ 900 trained experiences: 0.45
Average reward over those 100 experiences on model w/ 1000 trained experiences: -0.1
Average reward over those 100 experiences on model w/ 1100 trained experiences: 0.3
Average reward over those 100 experiences on model w/ 1200 trained experiences: 0.45
Average reward over those 100 experiences on model w/ 1300 trained experiences: 0.56
Average reward over those 100 experiences on model w/ 1400 trained experiences: 0.45
Average reward over those 100 experiences on model w/ 1500 trained experiences: 0.58
Average reward over those 100 experiences on model w/ 1600 trained experiences: 0.57
Average reward over those 100 experiences on model w/ 1700 trained experiences: 0.46
Average reward over those 100 experiences on model w/ 1800 trained experiences: 0.86
Average reward over those 100 experiences on model w/ 1900 trained experiences: 0.66
Average reward over those 100 experiences on model w/ 2000 trained experiences: 0.38
Average reward over those 100 experiences on model w/ 2100 trained experiences: 0.38
Average reward over those 100 experiences on model w/ 2200 trained experiences: 0.44
Average reward over those 100 experiences on model w/ 2300 trained experiences: 0.59
Average reward over those 100 experiences on model w/ 2400 trained experiences: 0.46
Average reward over those 100 experiences on model w/ 2500 trained experiences: 0.6
Average reward over those 100 experiences on model w/ 2600 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 2700 trained experiences: 0.43
Average reward over those 100 experiences on model w/ 2800 trained experiences: 0.57
Average reward over those 100 experiences on model w/ 2900 trained experiences: 0.32
Average reward over those 100 experiences on model w/ 3000 trained experiences: 0.66
Average reward over those 100 experiences on model w/ 3100 trained experiences: 0.65
Average reward over those 100 experiences on model w/ 3200 trained experiences: 0.54
Average reward over those 100 experiences on model w/ 3300 trained experiences: 0.57
Average reward over those 100 experiences on model w/ 3400 trained experiences: 0.66
Average reward over those 100 experiences on model w/ 3500 trained experiences: 0.62
Average reward over those 100 experiences on model w/ 3600 trained experiences: 0.6
Average reward over those 100 experiences on model w/ 3700 trained experiences: 0.69
Average reward over those 100 experiences on model w/ 3800 trained experiences: 0.59
Average reward over those 100 experiences on model w/ 3900 trained experiences: 0.72
Average reward over those 100 experiences on model w/ 4000 trained experiences: 0.87
Average reward over those 100 experiences on model w/ 4100 trained experiences: 0.92
Average reward over those 100 experiences on model w/ 4200 trained experiences: 0.65
Average reward over those 100 experiences on model w/ 4300 trained experiences: 0.58
Average reward over those 100 experiences on model w/ 4400 trained experiences: 0.56
Average reward over those 100 experiences on model w/ 4500 trained experiences: 0.86
Average reward over those 100 experiences on model w/ 4600 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 4700 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 4800 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 4900 trained experiences: 0.63
Average reward over those 100 experiences on model w/ 5000 trained experiences: 0.59
Average reward over those 100 experiences on model w/ 5100 trained experiences: 0.56
Average reward over those 100 experiences on model w/ 5200 trained experiences: 0.58
Average reward over those 100 experiences on model w/ 5300 trained experiences: 0.65
Average reward over those 100 experiences on model w/ 5400 trained experiences: 0.67
Average reward over those 100 experiences on model w/ 5500 trained experiences: 0.71
Average reward over those 100 experiences on model w/ 5600 trained experiences: 0.68
Average reward over those 100 experiences on model w/ 5700 trained experiences: 0.7
Average reward over those 100 experiences on model w/ 5800 trained experiences: 0.87
Average reward over those 100 experiences on model w/ 5900 trained experiences: 0.74
Average reward over those 100 experiences on model w/ 6000 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 6100 trained experiences: 0.78
Average reward over those 100 experiences on model w/ 6200 trained experiences: 0.68
Average reward over those 100 experiences on model w/ 6300 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 6400 trained experiences: 0.74
Average reward over those 100 experiences on model w/ 6500 trained experiences: 0.87
Average reward over those 100 experiences on model w/ 6600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 6700 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 6800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 6900 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 7000 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 7100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 7200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 7300 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 7400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 7500 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 7600 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 7700 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 7800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 7900 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 8000 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 8100 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 8200 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 8300 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 8400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 8500 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 8600 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 8700 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 8800 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 8900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 9000 trained experiences: 0.74
Average reward over those 100 experiences on model w/ 9100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 9200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 9300 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 9400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 9500 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 9600 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 9700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 9800 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 9900 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 10000 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 10100 trained experiences: 0.81
Average reward over those 100 experiences on model w/ 10200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 10300 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 10400 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 10500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 10600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 10700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 10800 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 10900 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 11000 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 0 trained experiences: -0.29
Average reward over those 100 experiences on model w/ 100 trained experiences: 0.43
Average reward over those 100 experiences on model w/ 200 trained experiences: 0.18
Average reward over those 100 experiences on model w/ 300 trained experiences: 0.3
Average reward over those 100 experiences on model w/ 400 trained experiences: 0.47
Average reward over those 100 experiences on model w/ 500 trained experiences: 0.43
Average reward over those 100 experiences on model w/ 600 trained experiences: 0.36
Average reward over those 100 experiences on model w/ 700 trained experiences: -0.19
Average reward over those 100 experiences on model w/ 800 trained experiences: 0.48
Average reward over those 100 experiences on model w/ 900 trained experiences: 0.29
Average reward over those 100 experiences on model w/ 1000 trained experiences: 0.5
Average reward over those 100 experiences on model w/ 1100 trained experiences: 0.41
Average reward over those 100 experiences on model w/ 1200 trained experiences: 0.43
Average reward over those 100 experiences on model w/ 1300 trained experiences: 0.47
Average reward over those 100 experiences on model w/ 1400 trained experiences: -0.02
Average reward over those 100 experiences on model w/ 1500 trained experiences: 0.46
Average reward over those 100 experiences on model w/ 1600 trained experiences: 0.45
Average reward over those 100 experiences on model w/ 1700 trained experiences: 0.39
Average reward over those 100 experiences on model w/ 1800 trained experiences: 0.36
Average reward over those 100 experiences on model w/ 1900 trained experiences: 0.47
Average reward over those 100 experiences on model w/ 2000 trained experiences: 0.13
Average reward over those 100 experiences on model w/ 2100 trained experiences: 0.37
Average reward over those 100 experiences on model w/ 2200 trained experiences: 0.68
Average reward over those 100 experiences on model w/ 2300 trained experiences: 0.61
Average reward over those 100 experiences on model w/ 2400 trained experiences: 0.4
Average reward over those 100 experiences on model w/ 2500 trained experiences: 0.49
Average reward over those 100 experiences on model w/ 2600 trained experiences: 0.43
Average reward over those 100 experiences on model w/ 2700 trained experiences: 0.58
Average reward over those 100 experiences on model w/ 2800 trained experiences: 0.63
Average reward over those 100 experiences on model w/ 2900 trained experiences: 0.36
Average reward over those 100 experiences on model w/ 3000 trained experiences: 0.69
Average reward over those 100 experiences on model w/ 3100 trained experiences: 0.63
Average reward over those 100 experiences on model w/ 3200 trained experiences: 0.86
Average reward over those 100 experiences on model w/ 3300 trained experiences: 0.74
Average reward over those 100 experiences on model w/ 3400 trained experiences: 0.57
Average reward over those 100 experiences on model w/ 3500 trained experiences: 0.65
Average reward over those 100 experiences on model w/ 3600 trained experiences: 0.71
Average reward over those 100 experiences on model w/ 3700 trained experiences: 0.81
Average reward over those 100 experiences on model w/ 3800 trained experiences: 0.61
Average reward over those 100 experiences on model w/ 3900 trained experiences: 0.72
Average reward over those 100 experiences on model w/ 4000 trained experiences: 0.51
Average reward over those 100 experiences on model w/ 4100 trained experiences: 0.68
Average reward over those 100 experiences on model w/ 4200 trained experiences: 0.52
Average reward over those 100 experiences on model w/ 4300 trained experiences: 0.87
Average reward over those 100 experiences on model w/ 4400 trained experiences: 0.42
Average reward over those 100 experiences on model w/ 4500 trained experiences: 0.86
Average reward over those 100 experiences on model w/ 4600 trained experiences: 0.63
Average reward over those 100 experiences on model w/ 4700 trained experiences: 0.75
Average reward over those 100 experiences on model w/ 4800 trained experiences: 0.69
Average reward over those 100 experiences on model w/ 4900 trained experiences: 0.78
Average reward over those 100 experiences on model w/ 5000 trained experiences: 0.54
Average reward over those 100 experiences on model w/ 5100 trained experiences: 0.69
Average reward over those 100 experiences on model w/ 5200 trained experiences: 0.64
Average reward over those 100 experiences on model w/ 5300 trained experiences: 0.71
Average reward over those 100 experiences on model w/ 5400 trained experiences: 0.46
Average reward over those 100 experiences on model w/ 5500 trained experiences: 0.73
Average reward over those 100 experiences on model w/ 5600 trained experiences: 0.7
Average reward over those 100 experiences on model w/ 5700 trained experiences: 0.68
Average reward over those 100 experiences on model w/ 5800 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 5900 trained experiences: 0.63
Average reward over those 100 experiences on model w/ 6000 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 6100 trained experiences: 0.86
Average reward over those 100 experiences on model w/ 6200 trained experiences: 0.75
Average reward over those 100 experiences on model w/ 6300 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 6400 trained experiences: 0.75
Average reward over those 100 experiences on model w/ 6500 trained experiences: 0.82
Average reward over those 100 experiences on model w/ 6600 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 6700 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 6800 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 6900 trained experiences: 0.77
Average reward over those 100 experiences on model w/ 7000 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 7100 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 7200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 7300 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 7400 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 7500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 7600 trained experiences: 0.71
Average reward over those 100 experiences on model w/ 7700 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 7800 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 7900 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 8000 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 8100 trained experiences: 0.65
Average reward over those 100 experiences on model w/ 8200 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 8300 trained experiences: 0.61
Average reward over those 100 experiences on model w/ 8400 trained experiences: 0.67
Average reward over those 100 experiences on model w/ 8500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 8600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 8700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 8800 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 8900 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 9000 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 9100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 9200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 9300 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 9400 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 9500 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 9600 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 9700 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 9800 trained experiences: 0.73
Average reward over those 100 experiences on model w/ 9900 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 10000 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 10100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 10200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 10300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 10400 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 10500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 10600 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 10700 trained experiences: 0.87
Average reward over those 100 experiences on model w/ 10800 trained experiences: 0.81
Average reward over those 100 experiences on model w/ 10900 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 11000 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 11100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 11200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 11300 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 11400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 11500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 11600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 11700 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 11800 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 11900 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 12000 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 12100 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 12200 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 12300 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 12400 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 12500 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 12600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 12700 trained experiences: 0.87
Average reward over those 100 experiences on model w/ 12800 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 12900 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 13000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 13100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 13200 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 13300 trained experiences: 0.74
Average reward over those 100 experiences on model w/ 13400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 13500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 13600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 13700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 13800 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 13900 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 14000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 14100 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 14200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 14300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 14400 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 14500 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 14600 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 14700 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 14800 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 14900 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 15000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 15100 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 15200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 15300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 15400 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 15500 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 15600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 15700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 15800 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 15900 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 16000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 16100 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 16200 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 16300 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 16400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 16500 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 16600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 16700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 16800 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 16900 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 17000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 17100 trained experiences: 0.62
Average reward over those 100 experiences on model w/ 17200 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 17300 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 17400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 17500 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 17600 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 17700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 17800 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 17900 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 18000 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 18100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 18200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 18300 trained experiences: 0.71
Average reward over those 100 experiences on model w/ 18400 trained experiences: 0.82
Average reward over those 100 experiences on model w/ 18500 trained experiences: 0.78
Average reward over those 100 experiences on model w/ 18600 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 18700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 18800 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 18900 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 19000 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 19100 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 19200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 19300 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 19400 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 19500 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 19600 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 19700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 19800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 19900 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 20000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 20100 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 20200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 20300 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 20400 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 20500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 20600 trained experiences: 0.72
Average reward over those 100 experiences on model w/ 20700 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 20800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 20900 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 21000 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 21100 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 21200 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 21300 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 21400 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 21500 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 21600 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 21700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 21800 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 21900 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 22000 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 22100 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 22200 trained experiences: 0.77
Average reward over those 100 experiences on model w/ 22300 trained experiences: 0.74
Average reward over those 100 experiences on model w/ 22400 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 22500 trained experiences: 0.77
Average reward over those 100 experiences on model w/ 22600 trained experiences: 0.87
Average reward over those 100 experiences on model w/ 22700 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 22800 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 22900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 23000 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 23100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 23200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 23300 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 23400 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 23500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 23600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 23700 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 23800 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 23900 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 24000 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 24100 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 24200 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 24300 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 24400 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 24500 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 24600 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 24700 trained experiences: 0.69
Average reward over those 100 experiences on model w/ 24800 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 24900 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 25000 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 25100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 25200 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 25300 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 25400 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 25500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 25600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 25700 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 25800 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 25900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 26000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 26100 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 26200 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 26300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 26400 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 26500 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 26600 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 26700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 26800 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 26900 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 27000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 27100 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 27200 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 27300 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 27400 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 27500 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 27600 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 27700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 27800 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 27900 trained experiences: 0.77
Average reward over those 100 experiences on model w/ 28000 trained experiences: 0.92
Average reward over those 100 experiences on model w/ 28100 trained experiences: 0.78
Average reward over those 100 experiences on model w/ 28200 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 28300 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 28400 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 28500 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 28600 trained experiences: 0.73
Average reward over those 100 experiences on model w/ 28700 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 28800 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 28900 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 29000 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 29100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 29200 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 29300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 29400 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 29500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 29600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 29700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 29800 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 29900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 30000 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 30100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 30200 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 30300 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 30400 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 30500 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 30600 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 30700 trained experiences: 0.92
Average reward over those 100 experiences on model w/ 30800 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 30900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 31000 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 31100 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 31200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 31300 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 31400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 31500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 31600 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 31700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 31800 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 31900 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 32000 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 32100 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 32200 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 32300 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 32400 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 32500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 32600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 32700 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 32800 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 32900 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 33000 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 33100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 33200 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 33300 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 33400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 33500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 33600 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 33700 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 33800 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 33900 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 34000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 34100 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 34200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 34300 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 34400 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 34500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 34600 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 34700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 34800 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 34900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 35000 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 35100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 35200 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 35300 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 35400 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 35500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 35600 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 35700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 35800 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 35900 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 36000 trained experiences: 0.78
Average reward over those 100 experiences on model w/ 36100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 36200 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 36300 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 36400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 36500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 36600 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 0 trained experiences: -0.18
Average reward over those 100 experiences on model w/ 100 trained experiences: 0.23
Average reward over those 100 experiences on model w/ 200 trained experiences: -0.26
Average reward over those 100 experiences on model w/ 300 trained experiences: 0.07
Average reward over those 100 experiences on model w/ 400 trained experiences: 0.22
Average reward over those 100 experiences on model w/ 500 trained experiences: 0.36
Average reward over those 100 experiences on model w/ 600 trained experiences: 0.23
Average reward over those 100 experiences on model w/ 700 trained experiences: 0.24
Average reward over those 100 experiences on model w/ 800 trained experiences: 0.5
Average reward over those 100 experiences on model w/ 900 trained experiences: 0.18
Average reward over those 100 experiences on model w/ 1000 trained experiences: 0.14
Average reward over those 100 experiences on model w/ 1100 trained experiences: 0.0
Average reward over those 100 experiences on model w/ 1200 trained experiences: 0.62
Average reward over those 100 experiences on model w/ 1300 trained experiences: 0.49
Average reward over those 100 experiences on model w/ 1400 trained experiences: 0.44
Average reward over those 100 experiences on model w/ 1500 trained experiences: 0.54
Average reward over those 100 experiences on model w/ 1600 trained experiences: 0.23
Average reward over those 100 experiences on model w/ 1700 trained experiences: 0.13
Average reward over those 100 experiences on model w/ 1800 trained experiences: 0.66
Average reward over those 100 experiences on model w/ 1900 trained experiences: -0.09
Average reward over those 100 experiences on model w/ 2000 trained experiences: 0.33
Average reward over those 100 experiences on model w/ 2100 trained experiences: 0.35
Average reward over those 100 experiences on model w/ 2200 trained experiences: 0.28
Average reward over those 100 experiences on model w/ 2300 trained experiences: 0.38
Average reward over those 100 experiences on model w/ 2400 trained experiences: 0.64
Average reward over those 100 experiences on model w/ 2500 trained experiences: 0.55
Average reward over those 100 experiences on model w/ 2600 trained experiences: 0.22
Average reward over those 100 experiences on model w/ 2700 trained experiences: 0.49
Average reward over those 100 experiences on model w/ 2800 trained experiences: 0.38
Average reward over those 100 experiences on model w/ 2900 trained experiences: 0.64
Average reward over those 100 experiences on model w/ 3000 trained experiences: 0.49
Average reward over those 100 experiences on model w/ 3100 trained experiences: 0.54
Average reward over those 100 experiences on model w/ 3200 trained experiences: 0.62
Average reward over those 100 experiences on model w/ 3300 trained experiences: 0.53
Average reward over those 100 experiences on model w/ 3400 trained experiences: 0.7
Average reward over those 100 experiences on model w/ 3500 trained experiences: 0.78
Average reward over those 100 experiences on model w/ 3600 trained experiences: 0.49
Average reward over those 100 experiences on model w/ 3700 trained experiences: 0.58
Average reward over those 100 experiences on model w/ 3800 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 3900 trained experiences: 0.66
Average reward over those 100 experiences on model w/ 4000 trained experiences: 0.56
Average reward over those 100 experiences on model w/ 4100 trained experiences: 0.81
Average reward over those 100 experiences on model w/ 4200 trained experiences: 0.47
Average reward over those 100 experiences on model w/ 4300 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 4400 trained experiences: 0.64
Average reward over those 100 experiences on model w/ 4500 trained experiences: 0.63
Average reward over those 100 experiences on model w/ 4600 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 4700 trained experiences: 0.78
Average reward over those 100 experiences on model w/ 4800 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 4900 trained experiences: 0.81
Average reward over those 100 experiences on model w/ 5000 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 5100 trained experiences: 0.77
Average reward over those 100 experiences on model w/ 5200 trained experiences: 0.75
Average reward over those 100 experiences on model w/ 5300 trained experiences: 0.69
Average reward over those 100 experiences on model w/ 5400 trained experiences: 0.87
Average reward over those 100 experiences on model w/ 5500 trained experiences: 0.66
Average reward over those 100 experiences on model w/ 5600 trained experiences: 0.72
Average reward over those 100 experiences on model w/ 5700 trained experiences: 0.78
Average reward over those 100 experiences on model w/ 5800 trained experiences: 0.73
Average reward over those 100 experiences on model w/ 5900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 6000 trained experiences: 0.73
Average reward over those 100 experiences on model w/ 6100 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 6200 trained experiences: 0.57
Average reward over those 100 experiences on model w/ 6300 trained experiences: 0.91
Average reward over those 100 experiences on model w/ 6400 trained experiences: 0.69
Average reward over those 100 experiences on model w/ 6500 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 6600 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 6700 trained experiences: 0.75
Average reward over those 100 experiences on model w/ 6800 trained experiences: 0.51
Average reward over those 100 experiences on model w/ 6900 trained experiences: 0.77
Average reward over those 100 experiences on model w/ 7000 trained experiences: 0.15
Average reward over those 100 experiences on model w/ 7100 trained experiences: 0.53
Average reward over those 100 experiences on model w/ 7200 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 7300 trained experiences: 0.74
Average reward over those 100 experiences on model w/ 7400 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 7500 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 7600 trained experiences: 0.68
Average reward over those 100 experiences on model w/ 7700 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 7800 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 7900 trained experiences: 0.75
Average reward over those 100 experiences on model w/ 8000 trained experiences: 0.6
Average reward over those 100 experiences on model w/ 8100 trained experiences: 0.57
Average reward over those 100 experiences on model w/ 8200 trained experiences: 0.56
Average reward over those 100 experiences on model w/ 8300 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 8400 trained experiences: 0.73
Average reward over those 100 experiences on model w/ 8500 trained experiences: 0.56
Average reward over those 100 experiences on model w/ 8600 trained experiences: 0.65
Average reward over those 100 experiences on model w/ 8700 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 8800 trained experiences: 0.73
Average reward over those 100 experiences on model w/ 8900 trained experiences: 0.71
Average reward over those 100 experiences on model w/ 9000 trained experiences: 0.71
Average reward over those 100 experiences on model w/ 9100 trained experiences: 0.74
Average reward over those 100 experiences on model w/ 9200 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 9300 trained experiences: 0.68
Average reward over those 100 experiences on model w/ 9400 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 9500 trained experiences: 0.87
Average reward over those 100 experiences on model w/ 9600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 9700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 9800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 9900 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 10000 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 10100 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 10200 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 10300 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 10400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 10500 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 10600 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 10700 trained experiences: 0.82
Average reward over those 100 experiences on model w/ 10800 trained experiences: 0.82
Average reward over those 100 experiences on model w/ 10900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 11000 trained experiences: 0.87
Average reward over those 100 experiences on model w/ 11100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 11200 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 11300 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 11400 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 11500 trained experiences: 0.67
Average reward over those 100 experiences on model w/ 11600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 11700 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 11800 trained experiences: 0.82
Average reward over those 100 experiences on model w/ 11900 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 12000 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 12100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 12200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 12300 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 12400 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 12500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 12600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 12700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 12800 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 12900 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 13000 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 13100 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 13200 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 13300 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 13400 trained experiences: 0.78
Average reward over those 100 experiences on model w/ 13500 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 13600 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 13700 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 13800 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 13900 trained experiences: 0.7
Average reward over those 100 experiences on model w/ 14000 trained experiences: 0.66
Average reward over those 100 experiences on model w/ 14100 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 14200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 14300 trained experiences: 0.82
Average reward over those 100 experiences on model w/ 14400 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 14500 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 14600 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 14700 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 14800 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 14900 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 15000 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 15100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 15200 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 15300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 15400 trained experiences: 0.71
Average reward over those 100 experiences on model w/ 15500 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 15600 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 15700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 15800 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 15900 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 16000 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 16100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 16200 trained experiences: 0.82
Average reward over those 100 experiences on model w/ 16300 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 16400 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 16500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 16600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 16700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 16800 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 16900 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 17000 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 17100 trained experiences: 0.76
Average reward over those 100 experiences on model w/ 17200 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 17300 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 17400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 17500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 17600 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 17700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 17800 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 17900 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 18000 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 18100 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 18200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 18300 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 18400 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 18500 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 18600 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 18700 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 18800 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 18900 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 19000 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 19100 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 19200 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 19300 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 19400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 19500 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 19600 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 19700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 19800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 19900 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 20000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 20100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 20200 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 20300 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 20400 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 20500 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 20600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 20700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 20800 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 20900 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 21000 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 21100 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 21200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 21300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 21400 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 21500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 21600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 21700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 21800 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 21900 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 22000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 22100 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 22200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 22300 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 22400 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 22500 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 22600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 22700 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 22800 trained experiences: 0.82
Average reward over those 100 experiences on model w/ 22900 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 23000 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 23100 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 23200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 23300 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 23400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 23500 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 23600 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 23700 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 23800 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 23900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 24000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 24100 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 24200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 24300 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 24400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 24500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 24600 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 24700 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 24800 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 24900 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 25000 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 25100 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 25200 trained experiences: 0.98
Average reward over those 100 experiences on model w/ 25300 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 25400 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 25500 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 25600 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 25700 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 25800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 25900 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 26000 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 26100 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 26200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 26300 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 26400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 26500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 26600 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 26700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 26800 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 26900 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 27000 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 27100 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 27200 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 27300 trained experiences: 0.87
Average reward over those 100 experiences on model w/ 27400 trained experiences: 0.67
Average reward over those 100 experiences on model w/ 27500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 27600 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 27700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 27800 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 27900 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 28000 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 28100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 28200 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 28300 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 28400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 28500 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 28600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 28700 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 28800 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 28900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 29000 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 29100 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 29200 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 29300 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 29400 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 29500 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 29600 trained experiences: 0.74
Average reward over those 100 experiences on model w/ 29700 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 29800 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 29900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 30000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 30100 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 30200 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 30300 trained experiences: 0.78
Average reward over those 100 experiences on model w/ 30400 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 30500 trained experiences: 0.71
Average reward over those 100 experiences on model w/ 30600 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 30700 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 30800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 30900 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 31000 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 31100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 31200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 31300 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 31400 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 31500 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 31600 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 31700 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 31800 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 31900 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 32000 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 32100 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 32200 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 32300 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 32400 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 32500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 32600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 32700 trained experiences: 0.68
Average reward over those 100 experiences on model w/ 32800 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 32900 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 33000 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 33100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 33200 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 33300 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 33400 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 33500 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 33600 trained experiences: 0.98
Average reward over those 100 experiences on model w/ 33700 trained experiences: 0.86
Average reward over those 100 experiences on model w/ 33800 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 33900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 34000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 34100 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 34200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 34300 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 34400 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 34500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 34600 trained experiences: 0.81
Average reward over those 100 experiences on model w/ 34700 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 34800 trained experiences: 0.41
Average reward over those 100 experiences on model w/ 34900 trained experiences: 0.78
Average reward over those 100 experiences on model w/ 35000 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 35100 trained experiences: 0.81
Average reward over those 100 experiences on model w/ 35200 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 35300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 35400 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 35500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 35600 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 35700 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 35800 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 35900 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 0 trained experiences: -0.17
Average reward over those 100 experiences on model w/ 100 trained experiences: 0.23
Average reward over those 100 experiences on model w/ 200 trained experiences: -0.21
Average reward over those 100 experiences on model w/ 300 trained experiences: 0.22
Average reward over those 100 experiences on model w/ 400 trained experiences: 0.2
Average reward over those 100 experiences on model w/ 500 trained experiences: 0.44
Average reward over those 100 experiences on model w/ 600 trained experiences: 0.23
Average reward over those 100 experiences on model w/ 700 trained experiences: 0.34
Average reward over those 100 experiences on model w/ 800 trained experiences: 0.45
Average reward over those 100 experiences on model w/ 900 trained experiences: 0.25
Average reward over those 100 experiences on model w/ 1000 trained experiences: 0.51
Average reward over those 100 experiences on model w/ 1100 trained experiences: 0.19
Average reward over those 100 experiences on model w/ 1200 trained experiences: 0.41
Average reward over those 100 experiences on model w/ 1300 trained experiences: 0.23
Average reward over those 100 experiences on model w/ 1400 trained experiences: 0.29
Average reward over those 100 experiences on model w/ 1500 trained experiences: 0.45
Average reward over those 100 experiences on model w/ 1600 trained experiences: 0.44
Average reward over those 100 experiences on model w/ 1700 trained experiences: 0.49
Average reward over those 100 experiences on model w/ 1800 trained experiences: 0.61
Average reward over those 100 experiences on model w/ 1900 trained experiences: 0.32
Average reward over those 100 experiences on model w/ 2000 trained experiences: 0.61
Average reward over those 100 experiences on model w/ 2100 trained experiences: 0.69
Average reward over those 100 experiences on model w/ 2200 trained experiences: 0.4
Average reward over those 100 experiences on model w/ 2300 trained experiences: 0.55
Average reward over those 100 experiences on model w/ 2400 trained experiences: 0.56
Average reward over those 100 experiences on model w/ 2500 trained experiences: 0.54
Average reward over those 100 experiences on model w/ 2600 trained experiences: 0.3
Average reward over those 100 experiences on model w/ 2700 trained experiences: 0.23
Average reward over those 100 experiences on model w/ 2800 trained experiences: 0.47
Average reward over those 100 experiences on model w/ 2900 trained experiences: 0.86
Average reward over those 100 experiences on model w/ 3000 trained experiences: 0.46
Average reward over those 100 experiences on model w/ 3100 trained experiences: 0.68
Average reward over those 100 experiences on model w/ 3200 trained experiences: 0.86
Average reward over those 100 experiences on model w/ 3300 trained experiences: 0.78
Average reward over those 100 experiences on model w/ 3400 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 3500 trained experiences: 0.59
Average reward over those 100 experiences on model w/ 3600 trained experiences: 0.6
Average reward over those 100 experiences on model w/ 3700 trained experiences: 0.67
Average reward over those 100 experiences on model w/ 3800 trained experiences: 0.57
Average reward over those 100 experiences on model w/ 3900 trained experiences: 0.72
Average reward over those 100 experiences on model w/ 4000 trained experiences: 0.77
Average reward over those 100 experiences on model w/ 4100 trained experiences: 0.6
Average reward over those 100 experiences on model w/ 4200 trained experiences: 0.64
Average reward over those 100 experiences on model w/ 4300 trained experiences: 0.78
Average reward over those 100 experiences on model w/ 4400 trained experiences: 0.65
Average reward over those 100 experiences on model w/ 4500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 4600 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 4700 trained experiences: 0.81
Average reward over those 100 experiences on model w/ 4800 trained experiences: 0.64
Average reward over those 100 experiences on model w/ 4900 trained experiences: 0.77
Average reward over those 100 experiences on model w/ 5000 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 5100 trained experiences: 0.92
Average reward over those 100 experiences on model w/ 5200 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 5300 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 5400 trained experiences: 0.87
Average reward over those 100 experiences on model w/ 5500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 5600 trained experiences: 0.78
Average reward over those 100 experiences on model w/ 5700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 5800 trained experiences: 0.82
Average reward over those 100 experiences on model w/ 5900 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 6000 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 6100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 6200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 6300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 6400 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 6500 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 6600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 6700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 6800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 6900 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 7000 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 7100 trained experiences: 0.81
Average reward over those 100 experiences on model w/ 7200 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 7300 trained experiences: 0.74
Average reward over those 100 experiences on model w/ 7400 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 7500 trained experiences: 0.86
Average reward over those 100 experiences on model w/ 7600 trained experiences: 0.78
Average reward over those 100 experiences on model w/ 7700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 7800 trained experiences: 0.78
Average reward over those 100 experiences on model w/ 7900 trained experiences: 0.78
Average reward over those 100 experiences on model w/ 8000 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 8100 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 8200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 8300 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 8400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 8500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 8600 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 8700 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 8800 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 8900 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 9000 trained experiences: 0.68
Average reward over those 100 experiences on model w/ 9100 trained experiences: 0.67
Average reward over those 100 experiences on model w/ 9200 trained experiences: 0.82
Average reward over those 100 experiences on model w/ 9300 trained experiences: 0.64
Average reward over those 100 experiences on model w/ 9400 trained experiences: 0.69
Average reward over those 100 experiences on model w/ 9500 trained experiences: 0.75
Average reward over those 100 experiences on model w/ 9600 trained experiences: 0.56
Average reward over those 100 experiences on model w/ 9700 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 9800 trained experiences: 0.92
Average reward over those 100 experiences on model w/ 9900 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 10000 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 10100 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 10200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 10300 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 10400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 10500 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 10600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 10700 trained experiences: 0.81
Average reward over those 100 experiences on model w/ 10800 trained experiences: 0.77
Average reward over those 100 experiences on model w/ 10900 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 11000 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 11100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 11200 trained experiences: 0.77
Average reward over those 100 experiences on model w/ 11300 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 11400 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 11500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 11600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 11700 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 11800 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 11900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 12000 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 12100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 12200 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 12300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 12400 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 12500 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 12600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 12700 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 12800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 12900 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 13000 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 13100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 13200 trained experiences: 0.81
Average reward over those 100 experiences on model w/ 13300 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 13400 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 13500 trained experiences: 0.82
Average reward over those 100 experiences on model w/ 13600 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 13700 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 13800 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 13900 trained experiences: 0.73
Average reward over those 100 experiences on model w/ 14000 trained experiences: 0.86
Average reward over those 100 experiences on model w/ 14100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 14200 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 14300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 14400 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 14500 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 14600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 14700 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 14800 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 14900 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 15000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 15100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 15200 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 15300 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 15400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 15500 trained experiences: 0.77
Average reward over those 100 experiences on model w/ 15600 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 15700 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 15800 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 15900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 16000 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 16100 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 16200 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 16300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 16400 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 16500 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 16600 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 16700 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 16800 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 16900 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 17000 trained experiences: 0.74
Average reward over those 100 experiences on model w/ 17100 trained experiences: 0.69
Average reward over those 100 experiences on model w/ 17200 trained experiences: 0.7
Average reward over those 100 experiences on model w/ 17300 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 17400 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 17500 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 17600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 17700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 17800 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 17900 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 18000 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 18100 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 18200 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 18300 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 18400 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 18500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 18600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 18700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 18800 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 18900 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 19000 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 19100 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 19200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 19300 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 19400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 19500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 19600 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 19700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 19800 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 19900 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 20000 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 20100 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 20200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 20300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 20400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 20500 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 20600 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 20700 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 20800 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 20900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 21000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 21100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 21200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 21300 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 21400 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 21500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 21600 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 21700 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 21800 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 21900 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 22000 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 22100 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 22200 trained experiences: 0.82
Average reward over those 100 experiences on model w/ 22300 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 22400 trained experiences: 0.71
Average reward over those 100 experiences on model w/ 22500 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 22600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 22700 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 22800 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 22900 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 23000 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 23100 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 23200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 23300 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 23400 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 23500 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 23600 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 23700 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 23800 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 23900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 24000 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 24100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 24200 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 24300 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 24400 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 24500 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 24600 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 24700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 24800 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 24900 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 25000 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 25100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 25200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 25300 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 25400 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 25500 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 25600 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 25700 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 25800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 25900 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 26000 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 26100 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 26200 trained experiences: 0.57
Average reward over those 100 experiences on model w/ 26300 trained experiences: 0.67
Average reward over those 100 experiences on model w/ 26400 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 26500 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 26600 trained experiences: 0.98
Average reward over those 100 experiences on model w/ 26700 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 26800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 26900 trained experiences: 0.82
Average reward over those 100 experiences on model w/ 27000 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 27100 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 27200 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 27300 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 27400 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 27500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 27600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 27700 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 27800 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 27900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 28000 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 28100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 28200 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 28300 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 28400 trained experiences: 0.77
Average reward over those 100 experiences on model w/ 28500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 28600 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 28700 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 28800 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 28900 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 29000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 29100 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 29200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 29300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 29400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 29500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 29600 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 29700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 29800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 29900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 30000 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 30100 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 30200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 30300 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 30400 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 30500 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 30600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 30700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 30800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 30900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 31000 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 31100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 31200 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 31300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 31400 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 31500 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 31600 trained experiences: 0.72
Average reward over those 100 experiences on model w/ 31700 trained experiences: 0.57
Average reward over those 100 experiences on model w/ 31800 trained experiences: 0.75
Average reward over those 100 experiences on model w/ 31900 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 32000 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 32100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 32200 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 32300 trained experiences: 0.81
Average reward over those 100 experiences on model w/ 32400 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 32500 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 32600 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 32700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 32800 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 32900 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 33000 trained experiences: 0.98
Average reward over those 100 experiences on model w/ 33100 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 33200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 33300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 33400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 33500 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 33600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 33700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 33800 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 33900 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 34000 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 34100 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 34200 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 34300 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 34400 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 34500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 34600 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 34700 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 34800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 34900 trained experiences: 0.82
Average reward over those 100 experiences on model w/ 35000 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 35100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 35200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 35300 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 35400 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 35500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 35600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 35700 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 35800 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 35900 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 36000 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 36100 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 36200 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 36300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 36400 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 36500 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 36600 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 36700 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 36800 trained experiences: 0.76
Average reward over those 100 experiences on model w/ 36900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 37000 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 37100 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 37200 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 37300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 37400 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 37500 trained experiences: 0.78
Average reward over those 100 experiences on model w/ 37600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 37700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 37800 trained experiences: 0.81
Average reward over those 100 experiences on model w/ 37900 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 38000 trained experiences: 0.76
Average reward over those 100 experiences on model w/ 38100 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 38200 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 38300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 38400 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 38500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 38600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 38700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 38800 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 38900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 39000 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 39100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 39200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 39300 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 39400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 39500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 39600 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 39700 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 39800 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 39900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 40000 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 40100 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 40200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 40300 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 40400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 40500 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 40600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 40700 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 40800 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 40900 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 41000 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 41100 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 41200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 41300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 41400 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 41500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 41600 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 41700 trained experiences: 0.68
Average reward over those 100 experiences on model w/ 41800 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 41900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 42000 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 42100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 42200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 42300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 42400 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 42500 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 42600 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 42700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 42800 trained experiences: 0.81
Average reward over those 100 experiences on model w/ 42900 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 43000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 43100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 43200 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 43300 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 43400 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 43500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 43600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 43700 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 43800 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 43900 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 44000 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 44100 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 44200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 44300 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 44400 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 44500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 44600 trained experiences: 0.72
Average reward over those 100 experiences on model w/ 44700 trained experiences: 0.74
Average reward over those 100 experiences on model w/ 44800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 44900 trained experiences: 0.72
Average reward over those 100 experiences on model w/ 45000 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 45100 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 45200 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 45300 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 45400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 45500 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 45600 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 45700 trained experiences: 0.73
Average reward over those 100 experiences on model w/ 45800 trained experiences: 0.74
Average reward over those 100 experiences on model w/ 45900 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 46000 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 46100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 46200 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 46300 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 46400 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 46500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 46600 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 46700 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 46800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 46900 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 47000 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 47100 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 47200 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 47300 trained experiences: 0.73
Average reward over those 100 experiences on model w/ 47400 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 47500 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 47600 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 47700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 47800 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 47900 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 48000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 48100 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 48200 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 48300 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 48400 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 48500 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 48600 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 48700 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 48800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 48900 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 49000 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 49100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 49200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 49300 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 49400 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 49500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 49600 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 49700 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 49800 trained experiences: 0.73
Average reward over those 100 experiences on model w/ 49900 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 50000 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 50100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 50200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 50300 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 50400 trained experiences: 0.82
Average reward over those 100 experiences on model w/ 50500 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 50600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 50700 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 50800 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 50900 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 51000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 51100 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 51200 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 51300 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 51400 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 51500 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 51600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 51700 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 51800 trained experiences: 0.58
Average reward over those 100 experiences on model w/ 51900 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 52000 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 52100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 52200 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 52300 trained experiences: 0.75
Average reward over those 100 experiences on model w/ 52400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 52500 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 52600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 52700 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 52800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 52900 trained experiences: 0.77
Average reward over those 100 experiences on model w/ 53000 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 53100 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 53200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 53300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 53400 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 53500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 53600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 53700 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 53800 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 53900 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 54000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 54100 trained experiences: 0.98
Average reward over those 100 experiences on model w/ 54200 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 54300 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 54400 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 54500 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 54600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 54700 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 54800 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 54900 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 55000 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 55100 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 55200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 55300 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 55400 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 55500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 55600 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 55700 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 55800 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 55900 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 56000 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 56100 trained experiences: 0.78
Average reward over those 100 experiences on model w/ 56200 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 56300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 56400 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 56500 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 56600 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 56700 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 56800 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 56900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 57000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 57100 trained experiences: 0.74
Average reward over those 100 experiences on model w/ 57200 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 57300 trained experiences: 0.74
Average reward over those 100 experiences on model w/ 57400 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 57500 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 57600 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 57700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 57800 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 57900 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 58000 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 58100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 58200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 58300 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 58400 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 58500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 58600 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 58700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 58800 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 58900 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 59000 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 59100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 59200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 59300 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 59400 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 59500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 59600 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 59700 trained experiences: 0.64
Average reward over those 100 experiences on model w/ 59800 trained experiences: 0.87
Average reward over those 100 experiences on model w/ 59900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 60000 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 60100 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 60200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 60300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 60400 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 60500 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 60600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 60700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 60800 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 60900 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 61000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 61100 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 61200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 61300 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 61400 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 61500 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 61600 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 61700 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 61800 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 61900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 62000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 62100 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 62200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 62300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 62400 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 62500 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 62600 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 62700 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 62800 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 62900 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 63000 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 63100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 63200 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 63300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 63400 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 63500 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 63600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 63700 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 63800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 63900 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 64000 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 64100 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 64200 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 64300 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 64400 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 64500 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 64600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 64700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 64800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 64900 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 65000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 65100 trained experiences: 0.74
Average reward over those 100 experiences on model w/ 65200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 65300 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 65400 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 65500 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 65600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 65700 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 65800 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 65900 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 66000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 66100 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 66200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 66300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 66400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 66500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 66600 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 66700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 66800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 66900 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 67000 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 67100 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 67200 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 67300 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 67400 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 67500 trained experiences: 0.85
Average reward over those 100 experiences on model w/ 67600 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 67700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 67800 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 67900 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 68000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 68100 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 68200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 68300 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 68400 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 68500 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 68600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 68700 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 68800 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 68900 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 69000 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 69100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 69200 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 69300 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 69400 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 69500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 69600 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 69700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 69800 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 69900 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 70000 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 70100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 70200 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 70300 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 70400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 70500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 70600 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 70700 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 70800 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 70900 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 71000 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 71100 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 71200 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 71300 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 71400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 71500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 71600 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 71700 trained experiences: 0.78
Average reward over those 100 experiences on model w/ 71800 trained experiences: 0.9
Average reward over those 100 experiences on model w/ 71900 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 72000 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 72100 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 72200 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 72300 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 72400 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 72500 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 72600 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 72700 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 72800 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 72900 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 73000 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 73100 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 73200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 73300 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 73400 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 73500 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 73600 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 73700 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 73800 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 73900 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 74000 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 74100 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 74200 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 74300 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 74400 trained experiences: 0.79
Average reward over those 100 experiences on model w/ 74500 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 74600 trained experiences: 0.93
Average reward over those 100 experiences on model w/ 74700 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 74800 trained experiences: 0.88
Average reward over those 100 experiences on model w/ 74900 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 75000 trained experiences: 0.86
Average reward over those 100 experiences on model w/ 75100 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 75200 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 75300 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 75400 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 75500 trained experiences: 0.8
Average reward over those 100 experiences on model w/ 75600 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 75700 trained experiences: 0.89
Average reward over those 100 experiences on model w/ 75800 trained experiences: 1.0
Average reward over those 100 experiences on model w/ 75900 trained experiences: 0.95
Average reward over those 100 experiences on model w/ 76000 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 76100 trained experiences: 0.99
Average reward over those 100 experiences on model w/ 76200 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 76300 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 76400 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 76500 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 76600 trained experiences: 0.84
Average reward over those 100 experiences on model w/ 76700 trained experiences: 0.94
Average reward over those 100 experiences on model w/ 76800 trained experiences: 0.83
Average reward over those 100 experiences on model w/ 76900 trained experiences: 0.95