ppo-Huggy / run_logs /timers.json
sunxysun's picture
Huggy
06dd526 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4037765264511108,
"min": 1.4037683010101318,
"max": 1.4255104064941406,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70795.2578125,
"min": 69039.6484375,
"max": 77103.9375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 81.80065359477125,
"min": 78.44356120826708,
"max": 396.9685039370079,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50062.0,
"min": 48894.0,
"max": 50415.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999938.0,
"min": 49821.0,
"max": 1999938.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999938.0,
"min": 49821.0,
"max": 1999938.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.454439878463745,
"min": 0.08380365371704102,
"max": 2.4744677543640137,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1502.1171875,
"min": 10.559260368347168,
"max": 1502.1171875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.793589810238165,
"min": 1.7923240455843152,
"max": 4.02854123556481,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2321.676963865757,
"min": 225.83282974362373,
"max": 2387.20966899395,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.793589810238165,
"min": 1.7923240455843152,
"max": 4.02854123556481,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2321.676963865757,
"min": 225.83282974362373,
"max": 2387.20966899395,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015872845770920522,
"min": 0.014120309238690728,
"max": 0.02062114335518951,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04761853731276157,
"min": 0.028240618477381456,
"max": 0.05491184781518921,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.056210507162743145,
"min": 0.023533911382158598,
"max": 0.061318106742368796,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16863152148822944,
"min": 0.047067822764317195,
"max": 0.1839543202271064,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.522198825966672e-06,
"min": 3.522198825966672e-06,
"max": 0.0002953455015515,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0566596477900016e-05,
"min": 1.0566596477900016e-05,
"max": 0.0008440177686607498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10117403333333334,
"min": 0.10117403333333334,
"max": 0.19844850000000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3035221,
"min": 0.20747955,
"max": 0.58133925,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.858426333333342e-05,
"min": 6.858426333333342e-05,
"max": 0.004922580149999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020575279000000025,
"min": 0.00020575279000000025,
"max": 0.014068828574999998,
"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": "1754126623",
"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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --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": "1754129509"
},
"total": 2886.1627411010004,
"count": 1,
"self": 0.49554283000088617,
"children": {
"run_training.setup": {
"total": 0.02406925999980558,
"count": 1,
"self": 0.02406925999980558
},
"TrainerController.start_learning": {
"total": 2885.6431290109995,
"count": 1,
"self": 4.995765084979666,
"children": {
"TrainerController._reset_env": {
"total": 3.613117762999991,
"count": 1,
"self": 3.613117762999991
},
"TrainerController.advance": {
"total": 2876.9209072100193,
"count": 232633,
"self": 5.387513863072854,
"children": {
"env_step": {
"total": 2329.6217678039175,
"count": 232633,
"self": 1834.950186441185,
"children": {
"SubprocessEnvManager._take_step": {
"total": 491.4998976848076,
"count": 232633,
"self": 17.72504405189693,
"children": {
"TorchPolicy.evaluate": {
"total": 473.77485363291066,
"count": 222943,
"self": 473.77485363291066
}
}
},
"workers": {
"total": 3.171683677924875,
"count": 232633,
"self": 0.0,
"children": {
"worker_root": {
"total": 2876.9664222961333,
"count": 232633,
"is_parallel": true,
"self": 1381.3132228962388,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009676150000359485,
"count": 1,
"is_parallel": true,
"self": 0.0002803100001074199,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006873049999285286,
"count": 2,
"is_parallel": true,
"self": 0.0006873049999285286
}
}
},
"UnityEnvironment.step": {
"total": 0.03560034700012693,
"count": 1,
"is_parallel": true,
"self": 0.0003244140000333573,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023353200003839447,
"count": 1,
"is_parallel": true,
"self": 0.00023353200003839447
},
"communicator.exchange": {
"total": 0.034251935000156664,
"count": 1,
"is_parallel": true,
"self": 0.034251935000156664
},
"steps_from_proto": {
"total": 0.0007904659998985153,
"count": 1,
"is_parallel": true,
"self": 0.00024186799987546692,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005485980000230484,
"count": 2,
"is_parallel": true,
"self": 0.0005485980000230484
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1495.6531993998944,
"count": 232632,
"is_parallel": true,
"self": 42.24222025100721,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 97.56179382900086,
"count": 232632,
"is_parallel": true,
"self": 97.56179382900086
},
"communicator.exchange": {
"total": 1255.394854311899,
"count": 232632,
"is_parallel": true,
"self": 1255.394854311899
},
"steps_from_proto": {
"total": 100.45433100798732,
"count": 232632,
"is_parallel": true,
"self": 37.7913055791023,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.66302542888502,
"count": 465264,
"is_parallel": true,
"self": 62.66302542888502
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 541.9116255430292,
"count": 232633,
"self": 7.451219847990387,
"children": {
"process_trajectory": {
"total": 193.4685155120394,
"count": 232633,
"self": 192.1364200120388,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3320955000006052,
"count": 10,
"self": 1.3320955000006052
}
}
},
"_update_policy": {
"total": 340.99189018299944,
"count": 97,
"self": 273.55137789400806,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.44051228899139,
"count": 2910,
"self": 67.44051228899139
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.720006346469745e-07,
"count": 1,
"self": 9.720006346469745e-07
},
"TrainerController._save_models": {
"total": 0.1133379809998587,
"count": 1,
"self": 0.002524104000258376,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11081387699960032,
"count": 1,
"self": 0.11081387699960032
}
}
}
}
}
}
}