{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.1730566024780273, "min": 1.8309533596038818, "max": 2.204400062561035, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 42904.828125, "min": 34041.0859375, "max": 48218.32421875, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 54.527472527472526, "min": 40.14876033057851, "max": 80.43548387096774, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19848.0, "min": 18400.0, "max": 20984.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1671.7175781316237, "min": 1616.3757031374112, "max": 1701.2952404224209, "count": 500 }, "SoccerTwos.Self-play.ELO.sum": { "value": 304252.5992199555, "min": 198091.82370366016, "max": 408352.25222034944, "count": 500 }, "SoccerTwos.Step.mean": { "value": 9999994.0, "min": 5009922.0, "max": 9999994.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 9999994.0, "min": 5009922.0, "max": 9999994.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.09265972673892975, "min": -0.11179759353399277, "max": 0.08839729428291321, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -16.864070892333984, "min": -20.063701629638672, "max": 16.128923416137695, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.09176599979400635, "min": -0.11218363046646118, "max": 0.08919791132211685, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -16.701412200927734, "min": -20.4212646484375, "max": 16.175819396972656, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.19895274593279913, "min": -0.3177415389281053, "max": 0.381910810599456, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -36.20939975976944, "min": -57.76840019226074, "max": 56.52279996871948, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.19895274593279913, "min": -0.3177415389281053, "max": 0.381910810599456, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -36.20939975976944, "min": -57.76840019226074, "max": 56.52279996871948, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01816240007416733, "min": 0.009453742671757937, "max": 0.02424842112814076, "count": 242 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01816240007416733, "min": 0.009453742671757937, "max": 0.02424842112814076, "count": 242 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.12518911063671112, "min": 0.09714691067735354, "max": 0.14615834653377532, "count": 242 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.12518911063671112, "min": 0.09714691067735354, "max": 0.14615834653377532, "count": 242 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.12596334367990494, "min": 0.09746019343535105, "max": 0.14700892567634583, "count": 242 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.12596334367990494, "min": 0.09746019343535105, "max": 0.14700892567634583, "count": 242 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 9.999999999999998e-05, "min": 9.999999999999998e-05, "max": 9.999999999999998e-05, "count": 242 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 9.999999999999998e-05, "min": 9.999999999999998e-05, "max": 9.999999999999998e-05, "count": 242 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 242 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 242 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 242 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 242 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678371195", "python_version": "3.9.13 (tags/v3.9.13:6de2ca5, May 17 2022, 16:36:42) [MSC v.1929 64 bit (AMD64)]", "command_line_arguments": "D:\\projects\\ml\\RL\\HuggingFace\\unit7\\ml-agents\\env2\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./ml-agents/training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cu116", "numpy_version": "1.21.2", "end_time_seconds": "1678396651" }, "total": 25479.1794367, "count": 1, "self": 2.2056270000030054, "children": { "run_training.setup": { "total": 0.32272980000000007, "count": 1, "self": 0.32272980000000007 }, "TrainerController.start_learning": { "total": 25476.6510799, "count": 1, "self": 10.667662699943321, "children": { "TrainerController._reset_env": { "total": 25.315599399985565, "count": 26, "self": 25.315599399985565 }, "TrainerController.advance": { "total": 25440.30213160007, "count": 347514, "self": 10.951096397908259, "children": { "env_step": { "total": 11400.541850101921, "count": 347514, "self": 6739.402310802918, "children": { "SubprocessEnvManager._take_step": { "total": 4654.842815399603, "count": 347514, "self": 70.09515529962937, "children": { "TorchPolicy.evaluate": { "total": 4584.7476600999735, "count": 627502, "self": 4584.7476600999735 } } }, "workers": { "total": 6.296723899400469, "count": 347514, "self": 0.0, "children": { "worker_root": { "total": 25454.82085710156, "count": 347514, "is_parallel": true, "self": 19867.6884203011, "children": { "steps_from_proto": { "total": 0.12746369999142182, "count": 52, "is_parallel": true, "self": 0.03029130001532021, "children": { "_process_rank_one_or_two_observation": { "total": 0.09717239997610161, "count": 208, "is_parallel": true, "self": 0.09717239997610161 } } }, "UnityEnvironment.step": { "total": 5587.004973100467, "count": 347514, "is_parallel": true, "self": 267.0280147018402, "children": { "UnityEnvironment._generate_step_input": { "total": 191.19602770105297, "count": 347514, "is_parallel": true, "self": 191.19602770105297 }, "communicator.exchange": { "total": 4296.945473098711, "count": 347514, "is_parallel": true, "self": 4296.945473098711 }, "steps_from_proto": { "total": 831.8354575988635, "count": 695028, "is_parallel": true, "self": 175.30384890347, "children": { "_process_rank_one_or_two_observation": { "total": 656.5316086953935, "count": 2780112, "is_parallel": true, "self": 656.5316086953935 } } } } } } } } } } }, "trainer_advance": { "total": 14028.809185100243, "count": 347514, "self": 70.33574869973017, "children": { "process_trajectory": { "total": 12226.992668600502, "count": 347514, "self": 12221.329717900504, "children": { "RLTrainer._checkpoint": { "total": 5.662950699997964, "count": 10, "self": 5.662950699997964 } } }, "_update_policy": { "total": 1731.4807678000097, "count": 242, "self": 943.0135480002068, "children": { "TorchPOCAOptimizer.update": { "total": 788.4672197998029, "count": 7260, "self": 788.4672197998029 } } } } } } }, "trainer_threads": { "total": 7.999988156370819e-07, "count": 1, "self": 7.999988156370819e-07 }, "TrainerController._save_models": { "total": 0.3656854000000749, "count": 1, "self": 0.003425500002776971, "children": { "RLTrainer._checkpoint": { "total": 0.3622598999972979, "count": 1, "self": 0.3622598999972979 } } } } } } }