zbenmo's picture
First Push
c9bd15d
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9211519956588745,
"min": 0.9211519956588745,
"max": 2.871791362762451,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8785.0263671875,
"min": 8785.0263671875,
"max": 29410.015625,
"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": 12.68292236328125,
"min": 0.3006066679954529,
"max": 12.68292236328125,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2473.169921875,
"min": 58.317691802978516,
"max": 2582.813720703125,
"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": 0.07534889354607074,
"min": 0.06556408173774422,
"max": 0.07534889354607074,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.301395574184283,
"min": 0.26531439541791124,
"max": 0.363311834873029,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19944254623032082,
"min": 0.10163103622457413,
"max": 0.289886946844704,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7977701849212833,
"min": 0.4065241448982965,
"max": 1.3662156407155241,
"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": 24.931818181818183,
"min": 3.0,
"max": 24.931818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1097.0,
"min": 132.0,
"max": 1363.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.931818181818183,
"min": 3.0,
"max": 24.931818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1097.0,
"min": 132.0,
"max": 1363.0,
"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": "1673870364",
"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": "1673870805"
},
"total": 441.152141175,
"count": 1,
"self": 0.3892348360000142,
"children": {
"run_training.setup": {
"total": 0.10863353000002007,
"count": 1,
"self": 0.10863353000002007
},
"TrainerController.start_learning": {
"total": 440.65427280899996,
"count": 1,
"self": 0.5487241120013664,
"children": {
"TrainerController._reset_env": {
"total": 9.97712159300005,
"count": 1,
"self": 9.97712159300005
},
"TrainerController.advance": {
"total": 430.0056919549985,
"count": 18202,
"self": 0.2848731690142472,
"children": {
"env_step": {
"total": 429.72081878598425,
"count": 18202,
"self": 281.14868506698264,
"children": {
"SubprocessEnvManager._take_step": {
"total": 148.26882533300227,
"count": 18202,
"self": 1.4393396850055638,
"children": {
"TorchPolicy.evaluate": {
"total": 146.8294856479967,
"count": 18202,
"self": 33.7422325819943,
"children": {
"TorchPolicy.sample_actions": {
"total": 113.0872530660024,
"count": 18202,
"self": 113.0872530660024
}
}
}
}
},
"workers": {
"total": 0.30330838599934395,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 439.35654164999914,
"count": 18202,
"is_parallel": true,
"self": 213.0348658510007,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.009685896999997112,
"count": 1,
"is_parallel": true,
"self": 0.003444769000054748,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.006241127999942364,
"count": 10,
"is_parallel": true,
"self": 0.006241127999942364
}
}
},
"UnityEnvironment.step": {
"total": 0.03216272000003073,
"count": 1,
"is_parallel": true,
"self": 0.0005212220000885281,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003499580000152491,
"count": 1,
"is_parallel": true,
"self": 0.0003499580000152491
},
"communicator.exchange": {
"total": 0.029470821999950658,
"count": 1,
"is_parallel": true,
"self": 0.029470821999950658
},
"steps_from_proto": {
"total": 0.0018207179999762957,
"count": 1,
"is_parallel": true,
"self": 0.0004263109999556036,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001394407000020692,
"count": 10,
"is_parallel": true,
"self": 0.001394407000020692
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 226.32167579899846,
"count": 18201,
"is_parallel": true,
"self": 8.589928152003154,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.996876931996383,
"count": 18201,
"is_parallel": true,
"self": 4.996876931996383
},
"communicator.exchange": {
"total": 181.7835005129994,
"count": 18201,
"is_parallel": true,
"self": 181.7835005129994
},
"steps_from_proto": {
"total": 30.95137020199951,
"count": 18201,
"is_parallel": true,
"self": 6.741182611992826,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.210187590006683,
"count": 182010,
"is_parallel": true,
"self": 24.210187590006683
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.518299999745068e-05,
"count": 1,
"self": 4.518299999745068e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 426.9968767430301,
"count": 348479,
"is_parallel": true,
"self": 9.956935028984844,
"children": {
"process_trajectory": {
"total": 243.92778438504547,
"count": 348479,
"is_parallel": true,
"self": 243.12792111004546,
"children": {
"RLTrainer._checkpoint": {
"total": 0.799863275000007,
"count": 4,
"is_parallel": true,
"self": 0.799863275000007
}
}
},
"_update_policy": {
"total": 173.11215732899979,
"count": 90,
"is_parallel": true,
"self": 43.6777410729984,
"children": {
"TorchPPOOptimizer.update": {
"total": 129.43441625600138,
"count": 4587,
"is_parallel": true,
"self": 129.43441625600138
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12268996600005266,
"count": 1,
"self": 0.0008511410001119657,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1218388249999407,
"count": 1,
"self": 0.1218388249999407
}
}
}
}
}
}
}