ppo-Pyramids / run_logs /timers.json
FlavienDeseure's picture
First Push
88a7f3c
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.2947351336479187,
"min": 0.28427809476852417,
"max": 1.426818609237671,
"count": 42
},
"Pyramids.Policy.Entropy.sum": {
"value": 8799.6123046875,
"min": 8646.6025390625,
"max": 43283.96875,
"count": 42
},
"Pyramids.Step.mean": {
"value": 1259901.0,
"min": 29952.0,
"max": 1259901.0,
"count": 42
},
"Pyramids.Step.sum": {
"value": 1259901.0,
"min": 29952.0,
"max": 1259901.0,
"count": 42
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5498011112213135,
"min": -0.10272380709648132,
"max": 0.7849849462509155,
"count": 42
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 152.29490661621094,
"min": -24.756437301635742,
"max": 226.07566833496094,
"count": 42
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.0073175206780433655,
"min": -0.027265027165412903,
"max": 0.3038255274295807,
"count": 42
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.0269532203674316,
"min": -7.797797679901123,
"max": 73.22195434570312,
"count": 42
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07460035995713302,
"min": 0.06393152023593068,
"max": 0.07572045740412756,
"count": 42
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0444050393998623,
"min": 0.51113745918559,
"max": 1.1358068610619134,
"count": 42
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01482533506766361,
"min": 0.0008656938796599014,
"max": 0.015751490415681878,
"count": 42
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.20755469094729054,
"min": 0.011254020435578719,
"max": 0.2362723562352282,
"count": 42
},
"Pyramids.Policy.LearningRate.mean": {
"value": 0.0001754471629461976,
"min": 0.0001754471629461976,
"max": 0.00029838354339596195,
"count": 42
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0024562602812467664,
"min": 0.0020886848037717336,
"max": 0.0038846892051036326,
"count": 42
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.15848237380952385,
"min": 0.15848237380952385,
"max": 0.19946118095238097,
"count": 42
},
"Pyramids.Policy.Epsilon.sum": {
"value": 2.218753233333334,
"min": 1.3962282666666668,
"max": 2.7224733000000003,
"count": 42
},
"Pyramids.Policy.Beta.mean": {
"value": 0.005852389143571429,
"min": 0.005852389143571429,
"max": 0.009946171977142856,
"count": 42
},
"Pyramids.Policy.Beta.sum": {
"value": 0.08193344801,
"min": 0.06962320384,
"max": 0.12950014703,
"count": 42
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.009499771520495415,
"min": 0.009296605363488197,
"max": 0.4660525619983673,
"count": 42
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1329967975616455,
"min": 0.1329967975616455,
"max": 3.2623679637908936,
"count": 42
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 308.968085106383,
"min": 269.1304347826087,
"max": 999.0,
"count": 42
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29043.0,
"min": 15984.0,
"max": 32933.0,
"count": 42
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5633340275033991,
"min": -1.0000000521540642,
"max": 1.7292844570916275,
"count": 42
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 146.95339858531952,
"min": -30.4700016528368,
"max": 200.59699702262878,
"count": 42
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5633340275033991,
"min": -1.0000000521540642,
"max": 1.7292844570916275,
"count": 42
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 146.95339858531952,
"min": -30.4700016528368,
"max": 200.59699702262878,
"count": 42
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.031098171069003155,
"min": 0.029887959644838702,
"max": 8.81314461864531,
"count": 42
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.9232280804862967,
"min": 2.8692441259045154,
"max": 141.01031389832497,
"count": 42
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 42
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 42
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1678108424",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.22.4",
"end_time_seconds": "1678111403"
},
"total": 2979.178132019,
"count": 1,
"self": 0.3960051069993824,
"children": {
"run_training.setup": {
"total": 0.21069229600016115,
"count": 1,
"self": 0.21069229600016115
},
"TrainerController.start_learning": {
"total": 2978.5714346160003,
"count": 1,
"self": 1.6549797709490122,
"children": {
"TrainerController._reset_env": {
"total": 6.649925075000283,
"count": 1,
"self": 6.649925075000283
},
"TrainerController.advance": {
"total": 2970.1245986810513,
"count": 81437,
"self": 1.8149374191611969,
"children": {
"env_step": {
"total": 2017.5021797369845,
"count": 81437,
"self": 1873.037714801157,
"children": {
"SubprocessEnvManager._take_step": {
"total": 143.44213510781992,
"count": 81437,
"self": 5.9414060807853275,
"children": {
"TorchPolicy.evaluate": {
"total": 137.5007290270346,
"count": 79393,
"self": 47.050057376162385,
"children": {
"TorchPolicy.sample_actions": {
"total": 90.45067165087221,
"count": 79393,
"self": 90.45067165087221
}
}
}
}
},
"workers": {
"total": 1.0223298280075142,
"count": 81436,
"self": 0.0,
"children": {
"worker_root": {
"total": 2972.306470701984,
"count": 81436,
"is_parallel": true,
"self": 1247.0254269940456,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002812773999721685,
"count": 1,
"is_parallel": true,
"self": 0.0009346189995085297,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018781550002131553,
"count": 8,
"is_parallel": true,
"self": 0.0018781550002131553
}
}
},
"UnityEnvironment.step": {
"total": 0.044754416000159836,
"count": 1,
"is_parallel": true,
"self": 0.0005317720001585258,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00048017300014180364,
"count": 1,
"is_parallel": true,
"self": 0.00048017300014180364
},
"communicator.exchange": {
"total": 0.042070567999871855,
"count": 1,
"is_parallel": true,
"self": 0.042070567999871855
},
"steps_from_proto": {
"total": 0.0016719029999876511,
"count": 1,
"is_parallel": true,
"self": 0.00045274100011738483,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012191619998702663,
"count": 8,
"is_parallel": true,
"self": 0.0012191619998702663
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1725.2810437079384,
"count": 81435,
"is_parallel": true,
"self": 40.37682073307769,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 29.843336602928048,
"count": 81435,
"is_parallel": true,
"self": 29.843336602928048
},
"communicator.exchange": {
"total": 1536.2810298220365,
"count": 81435,
"is_parallel": true,
"self": 1536.2810298220365
},
"steps_from_proto": {
"total": 118.77985654989607,
"count": 81435,
"is_parallel": true,
"self": 27.82841260611167,
"children": {
"_process_rank_one_or_two_observation": {
"total": 90.9514439437844,
"count": 651480,
"is_parallel": true,
"self": 90.9514439437844
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 950.8074815249056,
"count": 81436,
"self": 3.1216922378966956,
"children": {
"process_trajectory": {
"total": 211.70975352702317,
"count": 81436,
"self": 211.47191164002288,
"children": {
"RLTrainer._checkpoint": {
"total": 0.23784188700028608,
"count": 2,
"self": 0.23784188700028608
}
}
},
"_update_policy": {
"total": 735.9760357599857,
"count": 576,
"self": 283.82265159591316,
"children": {
"TorchPPOOptimizer.update": {
"total": 452.1533841640726,
"count": 28908,
"self": 452.1533841640726
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.6889998732949607e-06,
"count": 1,
"self": 1.6889998732949607e-06
},
"TrainerController._save_models": {
"total": 0.1419293999997535,
"count": 1,
"self": 0.0018774870004563127,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1400519129992972,
"count": 1,
"self": 0.1400519129992972
}
}
}
}
}
}
}