ppo-snowball / run_logs /timers.json
george-chen's picture
First push
459c3bd verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9525504112243652,
"min": 0.9525504112243652,
"max": 2.8328895568847656,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9053.0390625,
"min": 9053.0390625,
"max": 28918.13671875,
"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": 13.271925926208496,
"min": 0.1867181658744812,
"max": 13.271925926208496,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2588.025634765625,
"min": 36.223323822021484,
"max": 2692.28271484375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0676534584701594,
"min": 0.0632746768450506,
"max": 0.07480701013050481,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2706138338806376,
"min": 0.2530987073802024,
"max": 0.374035050652524,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.201753043295706,
"min": 0.1333620707691629,
"max": 0.30306608470923757,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.807012173182824,
"min": 0.5334482830766516,
"max": 1.3592904607454934,
"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": 25.59090909090909,
"min": 3.6818181818181817,
"max": 26.10909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1126.0,
"min": 162.0,
"max": 1436.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.59090909090909,
"min": 3.6818181818181817,
"max": 26.10909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1126.0,
"min": 162.0,
"max": 1436.0,
"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": "1749104776",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1749105216"
},
"total": 439.8479104439999,
"count": 1,
"self": 0.43684370799974204,
"children": {
"run_training.setup": {
"total": 0.023690216000090913,
"count": 1,
"self": 0.023690216000090913
},
"TrainerController.start_learning": {
"total": 439.3873765200001,
"count": 1,
"self": 0.3815758649872123,
"children": {
"TrainerController._reset_env": {
"total": 3.440882558999988,
"count": 1,
"self": 3.440882558999988
},
"TrainerController.advance": {
"total": 435.4806721000127,
"count": 18192,
"self": 0.41057820900959996,
"children": {
"env_step": {
"total": 308.7605959950097,
"count": 18192,
"self": 237.11159547103728,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.42591951499196,
"count": 18192,
"self": 1.2720607079877482,
"children": {
"TorchPolicy.evaluate": {
"total": 70.15385880700421,
"count": 18192,
"self": 70.15385880700421
}
}
},
"workers": {
"total": 0.22308100898044358,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 437.9221809780014,
"count": 18192,
"is_parallel": true,
"self": 230.30308522700295,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005949138000005405,
"count": 1,
"is_parallel": true,
"self": 0.004417741999873215,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015313960001321902,
"count": 10,
"is_parallel": true,
"self": 0.0015313960001321902
}
}
},
"UnityEnvironment.step": {
"total": 0.0379878879999751,
"count": 1,
"is_parallel": true,
"self": 0.0006241340000769924,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00037719899989951955,
"count": 1,
"is_parallel": true,
"self": 0.00037719899989951955
},
"communicator.exchange": {
"total": 0.035178625999947144,
"count": 1,
"is_parallel": true,
"self": 0.035178625999947144
},
"steps_from_proto": {
"total": 0.0018079290000514447,
"count": 1,
"is_parallel": true,
"self": 0.0003255599998510661,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014823690002003787,
"count": 10,
"is_parallel": true,
"self": 0.0014823690002003787
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 207.61909575099844,
"count": 18191,
"is_parallel": true,
"self": 9.933665213957852,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.45552645502778,
"count": 18191,
"is_parallel": true,
"self": 5.45552645502778
},
"communicator.exchange": {
"total": 160.76640985401048,
"count": 18191,
"is_parallel": true,
"self": 160.76640985401048
},
"steps_from_proto": {
"total": 31.463494228002332,
"count": 18191,
"is_parallel": true,
"self": 5.720508466985166,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.742985761017167,
"count": 181910,
"is_parallel": true,
"self": 25.742985761017167
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 126.30949789599345,
"count": 18192,
"self": 0.4920111719839042,
"children": {
"process_trajectory": {
"total": 27.870720460009352,
"count": 18192,
"self": 27.440072542009375,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4306479179999769,
"count": 4,
"self": 0.4306479179999769
}
}
},
"_update_policy": {
"total": 97.94676626400019,
"count": 90,
"self": 40.140064457000335,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.806701806999854,
"count": 4587,
"self": 57.806701806999854
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.420000424142927e-07,
"count": 1,
"self": 9.420000424142927e-07
},
"TrainerController._save_models": {
"total": 0.08424505400012094,
"count": 1,
"self": 0.0008767940000780072,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08336826000004294,
"count": 1,
"self": 0.08336826000004294
}
}
}
}
}
}
}