ppo-Huggy / run_logs /timers.json
exllos's picture
Huggy
c90b22e verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4011982679367065,
"min": 1.4011982679367065,
"max": 1.426325798034668,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70885.21875,
"min": 69103.0625,
"max": 77003.3359375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 71.82069970845481,
"min": 70.72596843615494,
"max": 396.484126984127,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49269.0,
"min": 49269.0,
"max": 50070.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999936.0,
"min": 49906.0,
"max": 1999936.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999936.0,
"min": 49906.0,
"max": 1999936.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.541959047317505,
"min": 0.11147093772888184,
"max": 2.5599944591522217,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1743.783935546875,
"min": 13.933867454528809,
"max": 1743.783935546875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.999672057242852,
"min": 1.844812082052231,
"max": 4.0145965113305975,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2743.7750312685966,
"min": 230.60151025652885,
"max": 2743.7750312685966,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.999672057242852,
"min": 1.844812082052231,
"max": 4.0145965113305975,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2743.7750312685966,
"min": 230.60151025652885,
"max": 2743.7750312685966,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015157440642643552,
"min": 0.01344068005491863,
"max": 0.019590328730070418,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04547232192793066,
"min": 0.02688136010983726,
"max": 0.05837814168771729,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06032121694750256,
"min": 0.021998608919481438,
"max": 0.06812039092183113,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18096365084250768,
"min": 0.043997217838962877,
"max": 0.20434259114166103,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.133948622049995e-06,
"min": 4.133948622049995e-06,
"max": 0.0002953224765591749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.2401845866149985e-05,
"min": 1.2401845866149985e-05,
"max": 0.0008441427186190999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10137795,
"min": 0.10137795,
"max": 0.19844082500000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30413385,
"min": 0.2078813,
"max": 0.5813809000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.875970499999992e-05,
"min": 7.875970499999992e-05,
"max": 0.004922197167499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00023627911499999975,
"min": 0.00023627911499999975,
"max": 0.014070906909999998,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1718807595",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1718810230"
},
"total": 2634.8220776589997,
"count": 1,
"self": 0.44165861300007236,
"children": {
"run_training.setup": {
"total": 0.05572511700006544,
"count": 1,
"self": 0.05572511700006544
},
"TrainerController.start_learning": {
"total": 2634.3246939289997,
"count": 1,
"self": 4.820962888077702,
"children": {
"TrainerController._reset_env": {
"total": 3.0519044920000624,
"count": 1,
"self": 3.0519044920000624
},
"TrainerController.advance": {
"total": 2626.345923789922,
"count": 233292,
"self": 5.042627336994428,
"children": {
"env_step": {
"total": 2092.2960539468772,
"count": 233292,
"self": 1709.6726591028291,
"children": {
"SubprocessEnvManager._take_step": {
"total": 379.4034278970223,
"count": 233292,
"self": 19.122962967856893,
"children": {
"TorchPolicy.evaluate": {
"total": 360.2804649291654,
"count": 222940,
"self": 360.2804649291654
}
}
},
"workers": {
"total": 3.219966947025682,
"count": 233292,
"self": 0.0,
"children": {
"worker_root": {
"total": 2626.4735640839467,
"count": 233292,
"is_parallel": true,
"self": 1255.779209012915,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009276980000549884,
"count": 1,
"is_parallel": true,
"self": 0.000240684000004876,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006870140000501124,
"count": 2,
"is_parallel": true,
"self": 0.0006870140000501124
}
}
},
"UnityEnvironment.step": {
"total": 0.033167757000001075,
"count": 1,
"is_parallel": true,
"self": 0.00035239299995737383,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018141300006391248,
"count": 1,
"is_parallel": true,
"self": 0.00018141300006391248
},
"communicator.exchange": {
"total": 0.03186990799997602,
"count": 1,
"is_parallel": true,
"self": 0.03186990799997602
},
"steps_from_proto": {
"total": 0.0007640430000037668,
"count": 1,
"is_parallel": true,
"self": 0.000213545999940834,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005504970000629328,
"count": 2,
"is_parallel": true,
"self": 0.0005504970000629328
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1370.6943550710316,
"count": 233291,
"is_parallel": true,
"self": 41.53227711309364,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 90.45416242001579,
"count": 233291,
"is_parallel": true,
"self": 90.45416242001579
},
"communicator.exchange": {
"total": 1139.7850982569867,
"count": 233291,
"is_parallel": true,
"self": 1139.7850982569867
},
"steps_from_proto": {
"total": 98.92281728093565,
"count": 233291,
"is_parallel": true,
"self": 37.023308312886115,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.89950896804953,
"count": 466582,
"is_parallel": true,
"self": 61.89950896804953
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 529.0072425060505,
"count": 233292,
"self": 6.967923213036443,
"children": {
"process_trajectory": {
"total": 173.53129682301517,
"count": 233292,
"self": 172.00095831701367,
"children": {
"RLTrainer._checkpoint": {
"total": 1.530338506001499,
"count": 10,
"self": 1.530338506001499
}
}
},
"_update_policy": {
"total": 348.5080224699989,
"count": 97,
"self": 282.1665239849899,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.34149848500897,
"count": 2910,
"self": 66.34149848500897
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.689999049238395e-07,
"count": 1,
"self": 8.689999049238395e-07
},
"TrainerController._save_models": {
"total": 0.10590189000004102,
"count": 1,
"self": 0.0018311809999431716,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10407070900009785,
"count": 1,
"self": 0.10407070900009785
}
}
}
}
}
}
}