ppo-Huggy / run_logs /timers.json
BrightCLASS's picture
Huggy
b71cd3f verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4078710079193115,
"min": 1.4078710079193115,
"max": 1.427890658378601,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70924.3203125,
"min": 69097.4296875,
"max": 77617.4765625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 80.37886178861788,
"min": 74.57034795763994,
"max": 413.2892561983471,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49433.0,
"min": 48917.0,
"max": 50016.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999946.0,
"min": 49408.0,
"max": 1999946.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999946.0,
"min": 49408.0,
"max": 1999946.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4536683559417725,
"min": 0.1294412612915039,
"max": 2.503927707672119,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1509.006103515625,
"min": 15.532951354980469,
"max": 1607.498046875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8708463607764827,
"min": 1.9391237781693538,
"max": 4.073415566350996,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2380.570511877537,
"min": 232.69485338032246,
"max": 2516.6770299077034,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8708463607764827,
"min": 1.9391237781693538,
"max": 4.073415566350996,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2380.570511877537,
"min": 232.69485338032246,
"max": 2516.6770299077034,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.013880637797733976,
"min": 0.01342194818353164,
"max": 0.019716430040231596,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.041641913393201925,
"min": 0.02684389636706328,
"max": 0.05498480881215073,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06440237429406907,
"min": 0.022561951105793315,
"max": 0.06440237429406907,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.19320712288220723,
"min": 0.04601930268108845,
"max": 0.19320712288220723,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.808948730383329e-06,
"min": 3.808948730383329e-06,
"max": 0.0002953525515491499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1426846191149987e-05,
"min": 1.1426846191149987e-05,
"max": 0.0008441083686305502,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10126961666666666,
"min": 0.10126961666666666,
"max": 0.19845084999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30380884999999996,
"min": 0.20770930000000004,
"max": 0.5813694500000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.335387166666662e-05,
"min": 7.335387166666662e-05,
"max": 0.004922697415,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022006161499999987,
"min": 0.00022006161499999987,
"max": 0.014070335555000002,
"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": "1729511383",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1729513813"
},
"total": 2430.812713767,
"count": 1,
"self": 0.47610474499970223,
"children": {
"run_training.setup": {
"total": 0.055906048999986524,
"count": 1,
"self": 0.055906048999986524
},
"TrainerController.start_learning": {
"total": 2430.280702973,
"count": 1,
"self": 4.433824389065194,
"children": {
"TrainerController._reset_env": {
"total": 4.269490302000008,
"count": 1,
"self": 4.269490302000008
},
"TrainerController.advance": {
"total": 2421.467049855935,
"count": 232996,
"self": 4.506818987968018,
"children": {
"env_step": {
"total": 1913.4372849609822,
"count": 232996,
"self": 1507.4951878309344,
"children": {
"SubprocessEnvManager._take_step": {
"total": 403.19625213006566,
"count": 232996,
"self": 15.612548223076374,
"children": {
"TorchPolicy.evaluate": {
"total": 387.5837039069893,
"count": 223002,
"self": 387.5837039069893
}
}
},
"workers": {
"total": 2.7458449999820687,
"count": 232996,
"self": 0.0,
"children": {
"worker_root": {
"total": 2423.156410381019,
"count": 232996,
"is_parallel": true,
"self": 1197.6368956401088,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008803860000625718,
"count": 1,
"is_parallel": true,
"self": 0.00026816500007953437,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006122209999830375,
"count": 2,
"is_parallel": true,
"self": 0.0006122209999830375
}
}
},
"UnityEnvironment.step": {
"total": 0.02910255800009054,
"count": 1,
"is_parallel": true,
"self": 0.00041360500017617596,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002173699999730161,
"count": 1,
"is_parallel": true,
"self": 0.0002173699999730161
},
"communicator.exchange": {
"total": 0.02775677799991172,
"count": 1,
"is_parallel": true,
"self": 0.02775677799991172
},
"steps_from_proto": {
"total": 0.000714805000029628,
"count": 1,
"is_parallel": true,
"self": 0.00019129600002543157,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005235090000041964,
"count": 2,
"is_parallel": true,
"self": 0.0005235090000041964
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1225.5195147409104,
"count": 232995,
"is_parallel": true,
"self": 37.87909798685041,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.11898152500987,
"count": 232995,
"is_parallel": true,
"self": 81.11898152500987
},
"communicator.exchange": {
"total": 1018.7073693940266,
"count": 232995,
"is_parallel": true,
"self": 1018.7073693940266
},
"steps_from_proto": {
"total": 87.81406583502348,
"count": 232995,
"is_parallel": true,
"self": 31.35026805284849,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.46379778217499,
"count": 465990,
"is_parallel": true,
"self": 56.46379778217499
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 503.5229459069848,
"count": 232996,
"self": 6.41290934209087,
"children": {
"process_trajectory": {
"total": 162.74140362189326,
"count": 232996,
"self": 161.28715657289342,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4542470489998323,
"count": 10,
"self": 1.4542470489998323
}
}
},
"_update_policy": {
"total": 334.36863294300065,
"count": 97,
"self": 268.39242157399906,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.97621136900159,
"count": 2910,
"self": 65.97621136900159
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.030000021273736e-06,
"count": 1,
"self": 1.030000021273736e-06
},
"TrainerController._save_models": {
"total": 0.11033739599997716,
"count": 1,
"self": 0.0019018940001842566,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1084355019997929,
"count": 1,
"self": 0.1084355019997929
}
}
}
}
}
}
}