gsotnikov's picture
First Push
7e8db42
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9692844152450562,
"min": 0.9682577848434448,
"max": 2.8594560623168945,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9340.0244140625,
"min": 9340.0244140625,
"max": 29378.05078125,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 11.986948013305664,
"min": 0.39220118522644043,
"max": 12.033708572387695,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2337.454833984375,
"min": 76.08702850341797,
"max": 2454.87646484375,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07384812047644564,
"min": 0.062394877205299376,
"max": 0.07384812047644564,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29539248190578254,
"min": 0.2495795088211975,
"max": 0.35639964514919875,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20786061744187392,
"min": 0.1409309476445082,
"max": 0.27949361130595207,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8314424697674957,
"min": 0.5637237905780328,
"max": 1.3645904797549344,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 23.318181818181817,
"min": 3.522727272727273,
"max": 23.8,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1026.0,
"min": 155.0,
"max": 1309.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.318181818181817,
"min": 3.522727272727273,
"max": 23.8,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1026.0,
"min": 155.0,
"max": 1309.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1685097804",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1685098275"
},
"total": 471.378961216,
"count": 1,
"self": 0.7446834390000276,
"children": {
"run_training.setup": {
"total": 0.04381679199991595,
"count": 1,
"self": 0.04381679199991595
},
"TrainerController.start_learning": {
"total": 470.59046098500005,
"count": 1,
"self": 0.5816827289824005,
"children": {
"TrainerController._reset_env": {
"total": 3.9104996459999484,
"count": 1,
"self": 3.9104996459999484
},
"TrainerController.advance": {
"total": 465.88650568101764,
"count": 18225,
"self": 0.273361749014839,
"children": {
"env_step": {
"total": 465.6131439320028,
"count": 18225,
"self": 343.0220953449965,
"children": {
"SubprocessEnvManager._take_step": {
"total": 122.3051003619978,
"count": 18225,
"self": 1.8745419069963418,
"children": {
"TorchPolicy.evaluate": {
"total": 120.43055845500146,
"count": 18225,
"self": 120.43055845500146
}
}
},
"workers": {
"total": 0.2859482250084966,
"count": 18225,
"self": 0.0,
"children": {
"worker_root": {
"total": 468.9241685729846,
"count": 18225,
"is_parallel": true,
"self": 217.4034600519791,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0052715119999220406,
"count": 1,
"is_parallel": true,
"self": 0.0038729859996919913,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013985260002300492,
"count": 10,
"is_parallel": true,
"self": 0.0013985260002300492
}
}
},
"UnityEnvironment.step": {
"total": 0.03684146900002361,
"count": 1,
"is_parallel": true,
"self": 0.0007574769999791897,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003343570000424734,
"count": 1,
"is_parallel": true,
"self": 0.0003343570000424734
},
"communicator.exchange": {
"total": 0.033286943999996765,
"count": 1,
"is_parallel": true,
"self": 0.033286943999996765
},
"steps_from_proto": {
"total": 0.0024626910000051794,
"count": 1,
"is_parallel": true,
"self": 0.0004619139997430466,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002000777000262133,
"count": 10,
"is_parallel": true,
"self": 0.002000777000262133
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 251.52070852100553,
"count": 18224,
"is_parallel": true,
"self": 9.896538205007118,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.270894787000998,
"count": 18224,
"is_parallel": true,
"self": 5.270894787000998
},
"communicator.exchange": {
"total": 203.29127157299172,
"count": 18224,
"is_parallel": true,
"self": 203.29127157299172
},
"steps_from_proto": {
"total": 33.0620039560057,
"count": 18224,
"is_parallel": true,
"self": 6.357507708996195,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.7044962470095,
"count": 182240,
"is_parallel": true,
"self": 26.7044962470095
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013729200009038323,
"count": 1,
"self": 0.00013729200009038323,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 462.4128718399912,
"count": 443663,
"is_parallel": true,
"self": 9.543312048975281,
"children": {
"process_trajectory": {
"total": 251.78015452201453,
"count": 443663,
"is_parallel": true,
"self": 250.18323062501463,
"children": {
"RLTrainer._checkpoint": {
"total": 1.596923896999897,
"count": 4,
"is_parallel": true,
"self": 1.596923896999897
}
}
},
"_update_policy": {
"total": 201.08940526900142,
"count": 90,
"is_parallel": true,
"self": 77.39377449500432,
"children": {
"TorchPPOOptimizer.update": {
"total": 123.6956307739971,
"count": 4587,
"is_parallel": true,
"self": 123.6956307739971
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.21163563699997212,
"count": 1,
"self": 0.0011137010001220915,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21052193599985003,
"count": 1,
"self": 0.21052193599985003
}
}
}
}
}
}
}