Spur1ous's picture
First Push
54f0933 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8147093653678894,
"min": 0.8147093653678894,
"max": 2.8659894466400146,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7742.99755859375,
"min": 7742.99755859375,
"max": 29256.01953125,
"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": 12.968544960021973,
"min": 0.3171442449092865,
"max": 12.968544960021973,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2528.8662109375,
"min": 61.52598571777344,
"max": 2632.106689453125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06977989678261129,
"min": 0.058880603273899074,
"max": 0.07483411362638934,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27911958713044516,
"min": 0.2355224130955963,
"max": 0.3741705681319467,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1956489209962242,
"min": 0.10977443992776575,
"max": 0.2759564344351198,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7825956839848968,
"min": 0.439097759711063,
"max": 1.299431951606975,
"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": 24.954545454545453,
"min": 3.159090909090909,
"max": 25.745454545454546,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1098.0,
"min": 139.0,
"max": 1416.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.954545454545453,
"min": 3.159090909090909,
"max": 25.745454545454546,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1098.0,
"min": 139.0,
"max": 1416.0,
"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": "1744007146",
"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 --force",
"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": "1744007575"
},
"total": 428.41911879500014,
"count": 1,
"self": 0.7809232160001329,
"children": {
"run_training.setup": {
"total": 0.030468639000105213,
"count": 1,
"self": 0.030468639000105213
},
"TrainerController.start_learning": {
"total": 427.6077269399999,
"count": 1,
"self": 0.3531388610090289,
"children": {
"TrainerController._reset_env": {
"total": 2.2604942059999757,
"count": 1,
"self": 2.2604942059999757
},
"TrainerController.advance": {
"total": 424.8586039069909,
"count": 18192,
"self": 0.34298558300645254,
"children": {
"env_step": {
"total": 300.113585799,
"count": 18192,
"self": 229.0635499340102,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.83854719798808,
"count": 18192,
"self": 1.2655432909887168,
"children": {
"TorchPolicy.evaluate": {
"total": 69.57300390699936,
"count": 18192,
"self": 69.57300390699936
}
}
},
"workers": {
"total": 0.2114886670017313,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 425.97274827200215,
"count": 18192,
"is_parallel": true,
"self": 224.72438378000913,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0023117000000638654,
"count": 1,
"is_parallel": true,
"self": 0.000741604000040752,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015700960000231134,
"count": 10,
"is_parallel": true,
"self": 0.0015700960000231134
}
}
},
"UnityEnvironment.step": {
"total": 0.034466489999999794,
"count": 1,
"is_parallel": true,
"self": 0.0005337580000741582,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00037170400003105897,
"count": 1,
"is_parallel": true,
"self": 0.00037170400003105897
},
"communicator.exchange": {
"total": 0.031722513999966395,
"count": 1,
"is_parallel": true,
"self": 0.031722513999966395
},
"steps_from_proto": {
"total": 0.0018385139999281819,
"count": 1,
"is_parallel": true,
"self": 0.00034073299991632666,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014977810000118552,
"count": 10,
"is_parallel": true,
"self": 0.0014977810000118552
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 201.24836449199302,
"count": 18191,
"is_parallel": true,
"self": 9.654578730023218,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.405846210996515,
"count": 18191,
"is_parallel": true,
"self": 5.405846210996515
},
"communicator.exchange": {
"total": 155.12607207998485,
"count": 18191,
"is_parallel": true,
"self": 155.12607207998485
},
"steps_from_proto": {
"total": 31.06186747098843,
"count": 18191,
"is_parallel": true,
"self": 5.492299425968099,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.569568045020333,
"count": 181910,
"is_parallel": true,
"self": 25.569568045020333
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 124.4020325249844,
"count": 18192,
"self": 0.45938371197769357,
"children": {
"process_trajectory": {
"total": 27.148739356006672,
"count": 18192,
"self": 26.544672902006823,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6040664539998488,
"count": 4,
"self": 0.6040664539998488
}
}
},
"_update_policy": {
"total": 96.79390945700004,
"count": 90,
"self": 38.46893192599782,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.32497753100222,
"count": 4587,
"self": 58.32497753100222
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.348000068901456e-06,
"count": 1,
"self": 1.348000068901456e-06
},
"TrainerController._save_models": {
"total": 0.13548861799995393,
"count": 1,
"self": 0.001211860999774217,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13427675700017971,
"count": 1,
"self": 0.13427675700017971
}
}
}
}
}
}
}