Amiko's picture
Test MLAgent
4ee97e9
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.957653284072876,
"min": 0.9365285634994507,
"max": 2.873471975326538,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9143.673828125,
"min": 9143.673828125,
"max": 29648.484375,
"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": 12.982518196105957,
"min": 0.31015583872795105,
"max": 12.982518196105957,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2531.591064453125,
"min": 60.17023468017578,
"max": 2648.119140625,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06882139098774595,
"min": 0.06435511972057273,
"max": 0.07339126960803552,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2752855639509838,
"min": 0.25780673138797283,
"max": 0.3669563480401776,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20453944327492338,
"min": 0.13187927257169182,
"max": 0.2889791881921245,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8181577730996935,
"min": 0.5275170902867673,
"max": 1.356811242068515,
"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": 25.681818181818183,
"min": 3.727272727272727,
"max": 25.681818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1130.0,
"min": 164.0,
"max": 1407.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.681818181818183,
"min": 3.727272727272727,
"max": 25.681818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1130.0,
"min": 164.0,
"max": 1407.0,
"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": "1676398513",
"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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget --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": "1.21.6",
"end_time_seconds": "1676398988"
},
"total": 474.26756031199994,
"count": 1,
"self": 0.43706352300000617,
"children": {
"run_training.setup": {
"total": 0.107478685999979,
"count": 1,
"self": 0.107478685999979
},
"TrainerController.start_learning": {
"total": 473.72301810299996,
"count": 1,
"self": 0.6004572680000706,
"children": {
"TrainerController._reset_env": {
"total": 10.668833790999997,
"count": 1,
"self": 10.668833790999997
},
"TrainerController.advance": {
"total": 462.3383213939998,
"count": 18201,
"self": 0.28741759599756733,
"children": {
"env_step": {
"total": 462.05090379800225,
"count": 18201,
"self": 319.41166447199754,
"children": {
"SubprocessEnvManager._take_step": {
"total": 142.3421725410047,
"count": 18201,
"self": 1.5192950650119883,
"children": {
"TorchPolicy.evaluate": {
"total": 140.8228774759927,
"count": 18201,
"self": 31.723906660000466,
"children": {
"TorchPolicy.sample_actions": {
"total": 109.09897081599223,
"count": 18201,
"self": 109.09897081599223
}
}
}
}
},
"workers": {
"total": 0.2970667850000268,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 472.0541556590048,
"count": 18201,
"is_parallel": true,
"self": 227.51461408600585,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005243246000020463,
"count": 1,
"is_parallel": true,
"self": 0.0030313539999724526,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022118920000480102,
"count": 10,
"is_parallel": true,
"self": 0.0022118920000480102
}
}
},
"UnityEnvironment.step": {
"total": 0.03706619900003716,
"count": 1,
"is_parallel": true,
"self": 0.00045609300002524833,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00033572500001355365,
"count": 1,
"is_parallel": true,
"self": 0.00033572500001355365
},
"communicator.exchange": {
"total": 0.03425815899998952,
"count": 1,
"is_parallel": true,
"self": 0.03425815899998952
},
"steps_from_proto": {
"total": 0.0020162220000088382,
"count": 1,
"is_parallel": true,
"self": 0.0004115849998811427,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016046370001276955,
"count": 10,
"is_parallel": true,
"self": 0.0016046370001276955
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 244.53954157299893,
"count": 18200,
"is_parallel": true,
"self": 9.807443626005181,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.252962278003906,
"count": 18200,
"is_parallel": true,
"self": 5.252962278003906
},
"communicator.exchange": {
"total": 197.58444017099066,
"count": 18200,
"is_parallel": true,
"self": 197.58444017099066
},
"steps_from_proto": {
"total": 31.89469549799918,
"count": 18200,
"is_parallel": true,
"self": 7.173903008982904,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.720792489016276,
"count": 182000,
"is_parallel": true,
"self": 24.720792489016276
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015491600004224892,
"count": 1,
"self": 0.00015491600004224892,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 458.92694754199806,
"count": 416318,
"is_parallel": true,
"self": 10.351915846978443,
"children": {
"process_trajectory": {
"total": 261.20247917101943,
"count": 416318,
"is_parallel": true,
"self": 260.1286414010195,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0738377699999546,
"count": 4,
"is_parallel": true,
"self": 1.0738377699999546
}
}
},
"_update_policy": {
"total": 187.37255252400018,
"count": 90,
"is_parallel": true,
"self": 65.07614038899806,
"children": {
"TorchPPOOptimizer.update": {
"total": 122.29641213500213,
"count": 4587,
"is_parallel": true,
"self": 122.29641213500213
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11525073400002839,
"count": 1,
"self": 0.0009616720000167334,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11428906200001165,
"count": 1,
"self": 0.11428906200001165
}
}
}
}
}
}
}