Akratos's picture
First Push
343bff6 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8967465758323669,
"min": 0.8967465758323669,
"max": 2.8547019958496094,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8522.6796875,
"min": 8522.6796875,
"max": 29140.796875,
"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": 13.00681209564209,
"min": 0.19769172370433807,
"max": 13.039373397827148,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2536.328369140625,
"min": 38.352195739746094,
"max": 2660.0322265625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0654157237104122,
"min": 0.06213616678048185,
"max": 0.07634887574771282,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2616628948416488,
"min": 0.2485446671219274,
"max": 0.37981356472443495,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19696833259042573,
"min": 0.12474311076962918,
"max": 0.29379140673314824,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7878733303617029,
"min": 0.49897244307851674,
"max": 1.4264636089404426,
"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.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.Environment.CumulativeReward.mean": {
"value": 25.045454545454547,
"min": 3.3181818181818183,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1102.0,
"min": 146.0,
"max": 1415.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.045454545454547,
"min": 3.3181818181818183,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1102.0,
"min": 146.0,
"max": 1415.0,
"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": "1742732566",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1742733161"
},
"total": 595.5413189450001,
"count": 1,
"self": 0.5932527840001285,
"children": {
"run_training.setup": {
"total": 0.04702319599994098,
"count": 1,
"self": 0.04702319599994098
},
"TrainerController.start_learning": {
"total": 594.901042965,
"count": 1,
"self": 0.641688815004386,
"children": {
"TrainerController._reset_env": {
"total": 4.955355424999993,
"count": 1,
"self": 4.955355424999993
},
"TrainerController.advance": {
"total": 589.2076171589956,
"count": 18192,
"self": 0.7215301759946442,
"children": {
"env_step": {
"total": 404.5464034169985,
"count": 18192,
"self": 342.3471523369926,
"children": {
"SubprocessEnvManager._take_step": {
"total": 61.81862455001044,
"count": 18192,
"self": 2.236457660007318,
"children": {
"TorchPolicy.evaluate": {
"total": 59.58216689000312,
"count": 18192,
"self": 59.58216689000312
}
}
},
"workers": {
"total": 0.3806265299954248,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 592.7519384590005,
"count": 18192,
"is_parallel": true,
"self": 297.8903556539964,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.009687600999995993,
"count": 1,
"is_parallel": true,
"self": 0.006480823999936547,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0032067770000594464,
"count": 10,
"is_parallel": true,
"self": 0.0032067770000594464
}
}
},
"UnityEnvironment.step": {
"total": 0.04586162800001148,
"count": 1,
"is_parallel": true,
"self": 0.0007607100001223444,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005864979999614661,
"count": 1,
"is_parallel": true,
"self": 0.0005864979999614661
},
"communicator.exchange": {
"total": 0.04212760499990509,
"count": 1,
"is_parallel": true,
"self": 0.04212760499990509
},
"steps_from_proto": {
"total": 0.0023868150000225796,
"count": 1,
"is_parallel": true,
"self": 0.0004726410001012482,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019141739999213314,
"count": 10,
"is_parallel": true,
"self": 0.0019141739999213314
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 294.8615828050041,
"count": 18191,
"is_parallel": true,
"self": 14.48507632397991,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.029473247004944,
"count": 18191,
"is_parallel": true,
"self": 8.029473247004944
},
"communicator.exchange": {
"total": 229.9694957890066,
"count": 18191,
"is_parallel": true,
"self": 229.9694957890066
},
"steps_from_proto": {
"total": 42.37753744501265,
"count": 18191,
"is_parallel": true,
"self": 8.28751697802386,
"children": {
"_process_rank_one_or_two_observation": {
"total": 34.09002046698879,
"count": 181910,
"is_parallel": true,
"self": 34.09002046698879
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 183.9396835660025,
"count": 18192,
"self": 0.8518249999794989,
"children": {
"process_trajectory": {
"total": 33.23213909302319,
"count": 18192,
"self": 32.77314674802312,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4589923450000697,
"count": 4,
"self": 0.4589923450000697
}
}
},
"_update_policy": {
"total": 149.8557194729998,
"count": 90,
"self": 53.86426135598708,
"children": {
"TorchPPOOptimizer.update": {
"total": 95.99145811701271,
"count": 4587,
"self": 95.99145811701271
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.092000047719921e-06,
"count": 1,
"self": 1.092000047719921e-06
},
"TrainerController._save_models": {
"total": 0.0963804739999432,
"count": 1,
"self": 0.0013595980001355201,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09502087599980769,
"count": 1,
"self": 0.09502087599980769
}
}
}
}
}
}
}