0xtimi's picture
First Push
f5174b3 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8430480360984802,
"min": 0.7739802598953247,
"max": 2.8445608615875244,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8012.32861328125,
"min": 7424.0185546875,
"max": 29037.27734375,
"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": 12.372431755065918,
"min": 0.33870115876197815,
"max": 12.381500244140625,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2412.624267578125,
"min": 65.70802307128906,
"max": 2521.3525390625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06643115093260456,
"min": 0.06386321666507808,
"max": 0.0812405908306805,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26572460373041823,
"min": 0.2554528666603123,
"max": 0.37812851882369847,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20137891794244447,
"min": 0.12922739679012082,
"max": 0.2979298340631466,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8055156717697779,
"min": 0.5169095871604833,
"max": 1.3647321468474818,
"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": 3.6136363636363638,
"max": 25.045454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1102.0,
"min": 159.0,
"max": 1334.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.045454545454547,
"min": 3.6136363636363638,
"max": 25.045454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1102.0,
"min": 159.0,
"max": 1334.0,
"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": "1757075600",
"python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
"command_line_arguments": "/home/tim/miniforge3/envs/rl-course-3.10.12/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": "1757075905"
},
"total": 304.12040745373815,
"count": 1,
"self": 0.2692014556378126,
"children": {
"run_training.setup": {
"total": 0.027330596931278706,
"count": 1,
"self": 0.027330596931278706
},
"TrainerController.start_learning": {
"total": 303.82387540116906,
"count": 1,
"self": 0.17368714837357402,
"children": {
"TrainerController._reset_env": {
"total": 1.832814103923738,
"count": 1,
"self": 1.832814103923738
},
"TrainerController.advance": {
"total": 301.71901055425406,
"count": 18192,
"self": 0.16770607931539416,
"children": {
"env_step": {
"total": 224.9856209368445,
"count": 18192,
"self": 188.9497131262906,
"children": {
"SubprocessEnvManager._take_step": {
"total": 35.92115123383701,
"count": 18192,
"self": 0.5623690988868475,
"children": {
"TorchPolicy.evaluate": {
"total": 35.35878213495016,
"count": 18192,
"self": 35.35878213495016
}
}
},
"workers": {
"total": 0.11475657671689987,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 303.2794372183271,
"count": 18192,
"is_parallel": true,
"self": 129.25692402059212,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0025386554189026356,
"count": 1,
"is_parallel": true,
"self": 0.0009087454527616501,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016299099661409855,
"count": 10,
"is_parallel": true,
"self": 0.0016299099661409855
}
}
},
"UnityEnvironment.step": {
"total": 0.019537424203008413,
"count": 1,
"is_parallel": true,
"self": 0.0004594484344124794,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003125779330730438,
"count": 1,
"is_parallel": true,
"self": 0.0003125779330730438
},
"communicator.exchange": {
"total": 0.01741478592157364,
"count": 1,
"is_parallel": true,
"self": 0.01741478592157364
},
"steps_from_proto": {
"total": 0.0013506119139492512,
"count": 1,
"is_parallel": true,
"self": 0.0002536480315029621,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001096963882446289,
"count": 10,
"is_parallel": true,
"self": 0.001096963882446289
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 174.02251319773495,
"count": 18191,
"is_parallel": true,
"self": 8.190668987110257,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.219799483194947,
"count": 18191,
"is_parallel": true,
"self": 4.219799483194947
},
"communicator.exchange": {
"total": 139.20493118837476,
"count": 18191,
"is_parallel": true,
"self": 139.20493118837476
},
"steps_from_proto": {
"total": 22.40711353905499,
"count": 18191,
"is_parallel": true,
"self": 3.73764601489529,
"children": {
"_process_rank_one_or_two_observation": {
"total": 18.6694675241597,
"count": 181910,
"is_parallel": true,
"self": 18.6694675241597
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 76.56568353809416,
"count": 18192,
"self": 0.19322001887485385,
"children": {
"process_trajectory": {
"total": 14.043137064669281,
"count": 18192,
"self": 14.043137064669281
},
"_update_policy": {
"total": 62.32932645455003,
"count": 90,
"self": 25.15794334653765,
"children": {
"TorchPPOOptimizer.update": {
"total": 37.17138310801238,
"count": 4587,
"self": 37.17138310801238
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.797483026981354e-07,
"count": 1,
"self": 5.797483026981354e-07
},
"TrainerController._save_models": {
"total": 0.09836301486939192,
"count": 1,
"self": 0.0009215958416461945,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09744141902774572,
"count": 1,
"self": 0.09744141902774572
}
}
}
}
}
}
}