ppo-Huggy / run_logs /timers.json
Fuyuxiang123's picture
Huggy
65f360e
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4013150930404663,
"min": 1.4013150930404663,
"max": 1.4240280389785767,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71105.53125,
"min": 69527.15625,
"max": 77473.015625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 73.12869822485207,
"min": 68.35644937586684,
"max": 397.42857142857144,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49435.0,
"min": 48719.0,
"max": 50076.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999989.0,
"min": 49498.0,
"max": 1999989.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999989.0,
"min": 49498.0,
"max": 1999989.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5471982955932617,
"min": 0.09225756675004959,
"max": 2.5471982955932617,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1721.9061279296875,
"min": 11.532196044921875,
"max": 1780.242919921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9947055742232758,
"min": 1.8103438513278962,
"max": 4.086120920521872,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2700.4209681749344,
"min": 226.29298141598701,
"max": 2816.2149002552032,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9947055742232758,
"min": 1.8103438513278962,
"max": 4.086120920521872,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2700.4209681749344,
"min": 226.29298141598701,
"max": 2816.2149002552032,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017776610790072783,
"min": 0.014980206190375612,
"max": 0.021833956058162587,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05332983237021835,
"min": 0.030016178781321894,
"max": 0.05433119678637013,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05945616679059135,
"min": 0.02128522703424096,
"max": 0.06214803730448087,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17836850037177404,
"min": 0.04257045406848192,
"max": 0.1861041388163964,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.977548674183338e-06,
"min": 3.977548674183338e-06,
"max": 0.000295280926573025,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1932646022550015e-05,
"min": 1.1932646022550015e-05,
"max": 0.0008438641687119501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10132581666666668,
"min": 0.10132581666666668,
"max": 0.198426975,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30397745000000004,
"min": 0.20779655000000008,
"max": 0.5812880500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.615825166666677e-05,
"min": 7.615825166666677e-05,
"max": 0.004921506052500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022847475500000028,
"min": 0.00022847475500000028,
"max": 0.014066273695,
"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": "1688458260",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1688460601"
},
"total": 2340.600216785,
"count": 1,
"self": 0.6782554160004111,
"children": {
"run_training.setup": {
"total": 0.041580827999951,
"count": 1,
"self": 0.041580827999951
},
"TrainerController.start_learning": {
"total": 2339.880380541,
"count": 1,
"self": 4.268137337950066,
"children": {
"TrainerController._reset_env": {
"total": 4.158146108999972,
"count": 1,
"self": 4.158146108999972
},
"TrainerController.advance": {
"total": 2331.2845464220495,
"count": 233938,
"self": 4.4322473870875,
"children": {
"env_step": {
"total": 1816.190200839,
"count": 233938,
"self": 1530.0416787029433,
"children": {
"SubprocessEnvManager._take_step": {
"total": 283.4060674830382,
"count": 233938,
"self": 16.614768998076215,
"children": {
"TorchPolicy.evaluate": {
"total": 266.791298484962,
"count": 222974,
"self": 266.791298484962
}
}
},
"workers": {
"total": 2.7424546530185125,
"count": 233938,
"self": 0.0,
"children": {
"worker_root": {
"total": 2332.0999990310365,
"count": 233938,
"is_parallel": true,
"self": 1081.8722270559315,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001435360999948898,
"count": 1,
"is_parallel": true,
"self": 0.0004513919998316851,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000983969000117213,
"count": 2,
"is_parallel": true,
"self": 0.000983969000117213
}
}
},
"UnityEnvironment.step": {
"total": 0.029566418000058547,
"count": 1,
"is_parallel": true,
"self": 0.0003565229997093411,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023995200012905116,
"count": 1,
"is_parallel": true,
"self": 0.00023995200012905116
},
"communicator.exchange": {
"total": 0.028239714000164895,
"count": 1,
"is_parallel": true,
"self": 0.028239714000164895
},
"steps_from_proto": {
"total": 0.0007302290000552603,
"count": 1,
"is_parallel": true,
"self": 0.00020706899977085413,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005231600002844061,
"count": 2,
"is_parallel": true,
"self": 0.0005231600002844061
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1250.227771975105,
"count": 233937,
"is_parallel": true,
"self": 39.055485062801154,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.17255346011825,
"count": 233937,
"is_parallel": true,
"self": 80.17255346011825
},
"communicator.exchange": {
"total": 1036.4620811492125,
"count": 233937,
"is_parallel": true,
"self": 1036.4620811492125
},
"steps_from_proto": {
"total": 94.53765230297313,
"count": 233937,
"is_parallel": true,
"self": 33.73230389790024,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.80534840507289,
"count": 467874,
"is_parallel": true,
"self": 60.80534840507289
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 510.6620981959618,
"count": 233938,
"self": 6.110839030053285,
"children": {
"process_trajectory": {
"total": 138.26522883790744,
"count": 233938,
"self": 137.02151967490727,
"children": {
"RLTrainer._checkpoint": {
"total": 1.243709163000176,
"count": 10,
"self": 1.243709163000176
}
}
},
"_update_policy": {
"total": 366.28603032800106,
"count": 97,
"self": 309.1300739110022,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.15595641699883,
"count": 2910,
"self": 57.15595641699883
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2450000212993473e-06,
"count": 1,
"self": 1.2450000212993473e-06
},
"TrainerController._save_models": {
"total": 0.16954942700022002,
"count": 1,
"self": 0.0026665420004974294,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1668828849997226,
"count": 1,
"self": 0.1668828849997226
}
}
}
}
}
}
}