Roberto's picture
hg first push
018bf44
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.895298957824707,
"min": 0.895298957824707,
"max": 2.861755847930908,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8548.314453125,
"min": 8548.314453125,
"max": 29307.2421875,
"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": 12.95840835571289,
"min": 0.3743203580379486,
"max": 12.95840835571289,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2526.8896484375,
"min": 72.61814880371094,
"max": 2633.7275390625,
"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": 0.06924321818537553,
"min": 0.06071020828139987,
"max": 0.07382922422843252,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2769728727415021,
"min": 0.2536787194834438,
"max": 0.3619471734518633,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20040757851857763,
"min": 0.10921537366412654,
"max": 0.2797591955784489,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8016303140743105,
"min": 0.43686149465650614,
"max": 1.3076020321425268,
"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": 25.931818181818183,
"min": 3.159090909090909,
"max": 25.931818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1141.0,
"min": 139.0,
"max": 1401.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.931818181818183,
"min": 3.159090909090909,
"max": 25.931818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1141.0,
"min": 139.0,
"max": 1401.0,
"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": "1673863867",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "0.29.0.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": "1673864354"
},
"total": 486.907974191,
"count": 1,
"self": 0.38870987900008913,
"children": {
"run_training.setup": {
"total": 0.10959962699999437,
"count": 1,
"self": 0.10959962699999437
},
"TrainerController.start_learning": {
"total": 486.40966468499994,
"count": 1,
"self": 0.6225702460067168,
"children": {
"TrainerController._reset_env": {
"total": 9.280716196000014,
"count": 1,
"self": 9.280716196000014
},
"TrainerController.advance": {
"total": 476.3659393689932,
"count": 18203,
"self": 0.3478397549930037,
"children": {
"env_step": {
"total": 476.0180996140002,
"count": 18203,
"self": 314.11936406199607,
"children": {
"SubprocessEnvManager._take_step": {
"total": 161.54845037800106,
"count": 18203,
"self": 1.7809457140016889,
"children": {
"TorchPolicy.evaluate": {
"total": 159.76750466399938,
"count": 18203,
"self": 36.14241361299844,
"children": {
"TorchPolicy.sample_actions": {
"total": 123.62509105100094,
"count": 18203,
"self": 123.62509105100094
}
}
}
}
},
"workers": {
"total": 0.35028517400309056,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 484.91362469400053,
"count": 18203,
"is_parallel": true,
"self": 231.5020337780084,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00492641399998206,
"count": 1,
"is_parallel": true,
"self": 0.002707334000007222,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002219079999974838,
"count": 10,
"is_parallel": true,
"self": 0.002219079999974838
}
}
},
"UnityEnvironment.step": {
"total": 0.036247952999985955,
"count": 1,
"is_parallel": true,
"self": 0.0005773249999947438,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000317691000020659,
"count": 1,
"is_parallel": true,
"self": 0.000317691000020659
},
"communicator.exchange": {
"total": 0.033358028999998623,
"count": 1,
"is_parallel": true,
"self": 0.033358028999998623
},
"steps_from_proto": {
"total": 0.001994907999971929,
"count": 1,
"is_parallel": true,
"self": 0.00044596400010732395,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015489439998646048,
"count": 10,
"is_parallel": true,
"self": 0.0015489439998646048
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 253.41159091599212,
"count": 18202,
"is_parallel": true,
"self": 9.52658634299246,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.742697782995265,
"count": 18202,
"is_parallel": true,
"self": 5.742697782995265
},
"communicator.exchange": {
"total": 202.5598034690018,
"count": 18202,
"is_parallel": true,
"self": 202.5598034690018
},
"steps_from_proto": {
"total": 35.582503321002605,
"count": 18202,
"is_parallel": true,
"self": 8.055542941989927,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.526960379012678,
"count": 182020,
"is_parallel": true,
"self": 27.526960379012678
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.062799993993394e-05,
"count": 1,
"self": 5.062799993993394e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 472.76664193404326,
"count": 393759,
"is_parallel": true,
"self": 10.79233854306824,
"children": {
"process_trajectory": {
"total": 271.9592353249749,
"count": 393759,
"is_parallel": true,
"self": 271.07731584897493,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8819194759999505,
"count": 4,
"is_parallel": true,
"self": 0.8819194759999505
}
}
},
"_update_policy": {
"total": 190.01506806600014,
"count": 90,
"is_parallel": true,
"self": 45.93433721800204,
"children": {
"TorchPPOOptimizer.update": {
"total": 144.0807308479981,
"count": 4587,
"is_parallel": true,
"self": 144.0807308479981
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14038824600004318,
"count": 1,
"self": 0.0009810320000269712,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1394072140000162,
"count": 1,
"self": 0.1394072140000162
}
}
}
}
}
}
}