S3S3's picture
Second Push
e2eb123
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9232625365257263,
"min": 0.9124116897583008,
"max": 2.8668861389160156,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8815.310546875,
"min": 8815.310546875,
"max": 29328.24609375,
"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": 13.187472343444824,
"min": 0.5105000734329224,
"max": 13.24532413482666,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2571.55712890625,
"min": 99.0370101928711,
"max": 2715.29150390625,
"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": 0.06454379617029118,
"min": 0.0620545835077863,
"max": 0.0754291734566305,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25817518468116474,
"min": 0.2482183340311452,
"max": 0.37714586728315247,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18730088615534352,
"min": 0.12477795054506072,
"max": 0.31081782263867996,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7492035446213741,
"min": 0.49911180218024287,
"max": 1.5540891131933998,
"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": 26.09090909090909,
"min": 3.840909090909091,
"max": 26.09090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1148.0,
"min": 169.0,
"max": 1431.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.09090909090909,
"min": 3.840909090909091,
"max": 26.09090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1148.0,
"min": 169.0,
"max": 1431.0,
"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": "1687978419",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1687978894"
},
"total": 474.58490468900004,
"count": 1,
"self": 0.4234270669999205,
"children": {
"run_training.setup": {
"total": 0.057770368000092276,
"count": 1,
"self": 0.057770368000092276
},
"TrainerController.start_learning": {
"total": 474.103707254,
"count": 1,
"self": 0.5536030220060866,
"children": {
"TrainerController._reset_env": {
"total": 5.024420632999977,
"count": 1,
"self": 5.024420632999977
},
"TrainerController.advance": {
"total": 468.3640790949937,
"count": 18201,
"self": 0.27081755199901636,
"children": {
"env_step": {
"total": 468.0932615429947,
"count": 18201,
"self": 343.64725767098787,
"children": {
"SubprocessEnvManager._take_step": {
"total": 124.17491943100367,
"count": 18201,
"self": 1.7423372780029922,
"children": {
"TorchPolicy.evaluate": {
"total": 122.43258215300068,
"count": 18201,
"self": 122.43258215300068
}
}
},
"workers": {
"total": 0.2710844410031541,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 472.57619871700183,
"count": 18201,
"is_parallel": true,
"self": 223.28362600300625,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002778692999982013,
"count": 1,
"is_parallel": true,
"self": 0.000696034999918993,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00208265800006302,
"count": 10,
"is_parallel": true,
"self": 0.00208265800006302
}
}
},
"UnityEnvironment.step": {
"total": 0.05920776699997532,
"count": 1,
"is_parallel": true,
"self": 0.0006091449999985343,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003388529999028833,
"count": 1,
"is_parallel": true,
"self": 0.0003388529999028833
},
"communicator.exchange": {
"total": 0.05590457300002072,
"count": 1,
"is_parallel": true,
"self": 0.05590457300002072
},
"steps_from_proto": {
"total": 0.0023551960000531835,
"count": 1,
"is_parallel": true,
"self": 0.0004441500001348686,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001911045999918315,
"count": 10,
"is_parallel": true,
"self": 0.001911045999918315
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 249.29257271399558,
"count": 18200,
"is_parallel": true,
"self": 10.206684486009294,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.275958631004983,
"count": 18200,
"is_parallel": true,
"self": 5.275958631004983
},
"communicator.exchange": {
"total": 198.3033843029947,
"count": 18200,
"is_parallel": true,
"self": 198.3033843029947
},
"steps_from_proto": {
"total": 35.50654529398662,
"count": 18200,
"is_parallel": true,
"self": 6.424576380962549,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.08196891302407,
"count": 182000,
"is_parallel": true,
"self": 29.08196891302407
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011943700019401149,
"count": 1,
"self": 0.00011943700019401149,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 464.6722021189745,
"count": 441474,
"is_parallel": true,
"self": 9.882809476964212,
"children": {
"process_trajectory": {
"total": 254.56374857400976,
"count": 441474,
"is_parallel": true,
"self": 252.5298654690099,
"children": {
"RLTrainer._checkpoint": {
"total": 2.033883104999859,
"count": 4,
"is_parallel": true,
"self": 2.033883104999859
}
}
},
"_update_policy": {
"total": 200.22564406800052,
"count": 90,
"is_parallel": true,
"self": 81.32699043900186,
"children": {
"TorchPPOOptimizer.update": {
"total": 118.89865362899866,
"count": 4587,
"is_parallel": true,
"self": 118.89865362899866
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.16148506700005782,
"count": 1,
"self": 0.0016213010001138173,
"children": {
"RLTrainer._checkpoint": {
"total": 0.159863765999944,
"count": 1,
"self": 0.159863765999944
}
}
}
}
}
}
}