chubbyk's picture
First Push
56fd6eb verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8524004220962524,
"min": 0.8524004220962524,
"max": 2.86445689201355,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8101.2138671875,
"min": 8101.2138671875,
"max": 29240.376953125,
"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": 12.871957778930664,
"min": 0.39376041293144226,
"max": 12.871957778930664,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2510.03173828125,
"min": 76.38951873779297,
"max": 2621.6494140625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0664512016947436,
"min": 0.06384120657557837,
"max": 0.07457979804974316,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2658048067789744,
"min": 0.2553648263023135,
"max": 0.37289899024871576,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20266783580768344,
"min": 0.10909720478743754,
"max": 0.2902143570576229,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8106713432307338,
"min": 0.43638881914975014,
"max": 1.4168580840615665,
"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": 25.40909090909091,
"min": 3.1363636363636362,
"max": 25.75,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1118.0,
"min": 138.0,
"max": 1393.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.40909090909091,
"min": 3.1363636363636362,
"max": 25.75,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1118.0,
"min": 138.0,
"max": 1393.0,
"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": "1769603627",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1769604057"
},
"total": 430.15840501699995,
"count": 1,
"self": 0.6937805109998862,
"children": {
"run_training.setup": {
"total": 0.03539878200012936,
"count": 1,
"self": 0.03539878200012936
},
"TrainerController.start_learning": {
"total": 429.42922572399993,
"count": 1,
"self": 0.34099446200161765,
"children": {
"TrainerController._reset_env": {
"total": 3.290338405000057,
"count": 1,
"self": 3.290338405000057
},
"TrainerController.advance": {
"total": 425.6906322229984,
"count": 18192,
"self": 0.35700604497378663,
"children": {
"env_step": {
"total": 307.2197019880266,
"count": 18192,
"self": 240.9163162630341,
"children": {
"SubprocessEnvManager._take_step": {
"total": 66.09981883898718,
"count": 18192,
"self": 1.2043768559890395,
"children": {
"TorchPolicy.evaluate": {
"total": 64.89544198299814,
"count": 18192,
"self": 64.89544198299814
}
}
},
"workers": {
"total": 0.20356688600531925,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 427.4926160790244,
"count": 18192,
"is_parallel": true,
"self": 215.81954152801495,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0056848409999474825,
"count": 1,
"is_parallel": true,
"self": 0.0037474760003988195,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001937364999548663,
"count": 10,
"is_parallel": true,
"self": 0.001937364999548663
}
}
},
"UnityEnvironment.step": {
"total": 0.03410415899998043,
"count": 1,
"is_parallel": true,
"self": 0.0005582829999184469,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004065279999849736,
"count": 1,
"is_parallel": true,
"self": 0.0004065279999849736
},
"communicator.exchange": {
"total": 0.03125182200005838,
"count": 1,
"is_parallel": true,
"self": 0.03125182200005838
},
"steps_from_proto": {
"total": 0.0018875260000186245,
"count": 1,
"is_parallel": true,
"self": 0.0003679360002024623,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015195899998161622,
"count": 10,
"is_parallel": true,
"self": 0.0015195899998161622
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 211.67307455100945,
"count": 18191,
"is_parallel": true,
"self": 10.08836224104607,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.256903050988967,
"count": 18191,
"is_parallel": true,
"self": 5.256903050988967
},
"communicator.exchange": {
"total": 161.57022722498755,
"count": 18191,
"is_parallel": true,
"self": 161.57022722498755
},
"steps_from_proto": {
"total": 34.757582033986864,
"count": 18191,
"is_parallel": true,
"self": 6.489451861019688,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.268130172967176,
"count": 181910,
"is_parallel": true,
"self": 28.268130172967176
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 118.11392418999799,
"count": 18192,
"self": 0.4589351770137,
"children": {
"process_trajectory": {
"total": 25.355390260985814,
"count": 18192,
"self": 24.833206011985794,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5221842490000199,
"count": 4,
"self": 0.5221842490000199
}
}
},
"_update_policy": {
"total": 92.29959875199847,
"count": 90,
"self": 38.1317490319891,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.16784972000937,
"count": 4587,
"self": 54.16784972000937
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2189998415124137e-06,
"count": 1,
"self": 1.2189998415124137e-06
},
"TrainerController._save_models": {
"total": 0.1072594150000441,
"count": 1,
"self": 0.0008781689998613729,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10638124600018273,
"count": 1,
"self": 0.10638124600018273
}
}
}
}
}
}
}