wangxso's picture
First Push
e05873b
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9232401847839355,
"min": 0.9127326607704163,
"max": 2.8653416633605957,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8845.564453125,
"min": 8845.564453125,
"max": 29375.482421875,
"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": 12.882811546325684,
"min": 0.430304616689682,
"max": 12.882811546325684,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2512.148193359375,
"min": 83.47909545898438,
"max": 2627.43359375,
"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": 0.06347564367388259,
"min": 0.06347564367388259,
"max": 0.07552571024222975,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25390257469553035,
"min": 0.25390257469553035,
"max": 0.3729034401807368,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2337930569169568,
"min": 0.12856246987083816,
"max": 0.2658870346552017,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9351722276678271,
"min": 0.5142498794833527,
"max": 1.2720611165551579,
"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": 25.40909090909091,
"min": 3.727272727272727,
"max": 25.40909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1118.0,
"min": 164.0,
"max": 1377.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.40909090909091,
"min": 3.727272727272727,
"max": 25.40909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1118.0,
"min": 164.0,
"max": 1377.0,
"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": "1691999176",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"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": "1691999647"
},
"total": 471.14794435100004,
"count": 1,
"self": 0.38491406399998596,
"children": {
"run_training.setup": {
"total": 0.04476152299997693,
"count": 1,
"self": 0.04476152299997693
},
"TrainerController.start_learning": {
"total": 470.7182687640001,
"count": 1,
"self": 0.5057771699926548,
"children": {
"TrainerController._reset_env": {
"total": 4.662034590000019,
"count": 1,
"self": 4.662034590000019
},
"TrainerController.advance": {
"total": 465.4082812740073,
"count": 18203,
"self": 0.26665112500523946,
"children": {
"env_step": {
"total": 465.1416301490021,
"count": 18203,
"self": 338.29668624099514,
"children": {
"SubprocessEnvManager._take_step": {
"total": 126.5715407160032,
"count": 18203,
"self": 1.7075562820107848,
"children": {
"TorchPolicy.evaluate": {
"total": 124.86398443399241,
"count": 18203,
"self": 124.86398443399241
}
}
},
"workers": {
"total": 0.27340319200374097,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 469.1937569530039,
"count": 18203,
"is_parallel": true,
"self": 225.12704739701002,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006374174999962179,
"count": 1,
"is_parallel": true,
"self": 0.004686089000074389,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016880859998877895,
"count": 10,
"is_parallel": true,
"self": 0.0016880859998877895
}
}
},
"UnityEnvironment.step": {
"total": 0.11293364199997313,
"count": 1,
"is_parallel": true,
"self": 0.0006166379999399396,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004504500000166445,
"count": 1,
"is_parallel": true,
"self": 0.0004504500000166445
},
"communicator.exchange": {
"total": 0.10952045999999882,
"count": 1,
"is_parallel": true,
"self": 0.10952045999999882
},
"steps_from_proto": {
"total": 0.002346094000017729,
"count": 1,
"is_parallel": true,
"self": 0.00041370599990386836,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019323880001138605,
"count": 10,
"is_parallel": true,
"self": 0.0019323880001138605
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 244.0667095559939,
"count": 18202,
"is_parallel": true,
"self": 10.583004134993473,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.246659648007039,
"count": 18202,
"is_parallel": true,
"self": 5.246659648007039
},
"communicator.exchange": {
"total": 192.67361741899896,
"count": 18202,
"is_parallel": true,
"self": 192.67361741899896
},
"steps_from_proto": {
"total": 35.563428353994425,
"count": 18202,
"is_parallel": true,
"self": 6.402769539011956,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.16065881498247,
"count": 182020,
"is_parallel": true,
"self": 29.16065881498247
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013252600001578685,
"count": 1,
"self": 0.00013252600001578685,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 461.9528057769928,
"count": 435559,
"is_parallel": true,
"self": 9.4821818129941,
"children": {
"process_trajectory": {
"total": 250.31979899399892,
"count": 435559,
"is_parallel": true,
"self": 249.5430211619988,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7767778320001071,
"count": 4,
"is_parallel": true,
"self": 0.7767778320001071
}
}
},
"_update_policy": {
"total": 202.1508249699998,
"count": 90,
"is_parallel": true,
"self": 82.15664605499728,
"children": {
"TorchPPOOptimizer.update": {
"total": 119.99417891500252,
"count": 4587,
"is_parallel": true,
"self": 119.99417891500252
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14204320400006054,
"count": 1,
"self": 0.0008596470000838963,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14118355699997664,
"count": 1,
"self": 0.14118355699997664
}
}
}
}
}
}
}