ppo-Huggy / run_logs /timers.json
claybowser's picture
Huggy
ae4ead9 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.407225251197815,
"min": 1.407225251197815,
"max": 1.427651047706604,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70666.6328125,
"min": 69655.03125,
"max": 76101.4921875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 91.2279411764706,
"min": 88.54838709677419,
"max": 389.9609375,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49628.0,
"min": 48859.0,
"max": 50142.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999499.0,
"min": 49819.0,
"max": 1999499.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999499.0,
"min": 49819.0,
"max": 1999499.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4552712440490723,
"min": 0.06251228600740433,
"max": 2.4948222637176514,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1335.6676025390625,
"min": 7.939060688018799,
"max": 1335.6676025390625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8181660196141287,
"min": 1.8226096407165677,
"max": 3.9176063323632264,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2077.082314670086,
"min": 231.4714243710041,
"max": 2115.7750759124756,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8181660196141287,
"min": 1.8226096407165677,
"max": 3.9176063323632264,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2077.082314670086,
"min": 231.4714243710041,
"max": 2115.7750759124756,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016531248106103805,
"min": 0.01441552901136068,
"max": 0.021513903387434162,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.049593744318311414,
"min": 0.02883105802272136,
"max": 0.06381432210509956,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05151838730606768,
"min": 0.024100065645244386,
"max": 0.05767571441829204,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15455516191820304,
"min": 0.05040926020592451,
"max": 0.16650110768775145,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3768988744000013e-06,
"min": 3.3768988744000013e-06,
"max": 0.000295315876561375,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0130696623200004e-05,
"min": 1.0130696623200004e-05,
"max": 0.0008441652186116,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10112560000000002,
"min": 0.10112560000000002,
"max": 0.19843862500000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30337680000000006,
"min": 0.20738084999999998,
"max": 0.5813884,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.616744000000005e-05,
"min": 6.616744000000005e-05,
"max": 0.0049220873875,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019850232000000014,
"min": 0.00019850232000000014,
"max": 0.014071281159999999,
"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": "1731506199",
"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": "2.5.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1731508631"
},
"total": 2431.669109675,
"count": 1,
"self": 0.43672263600001315,
"children": {
"run_training.setup": {
"total": 0.05408794299995634,
"count": 1,
"self": 0.05408794299995634
},
"TrainerController.start_learning": {
"total": 2431.178299096,
"count": 1,
"self": 4.4156374969825265,
"children": {
"TrainerController._reset_env": {
"total": 6.035379417999991,
"count": 1,
"self": 6.035379417999991
},
"TrainerController.advance": {
"total": 2420.6062558430176,
"count": 231764,
"self": 4.7515792630028955,
"children": {
"env_step": {
"total": 1900.6944947770112,
"count": 231764,
"self": 1494.8960189440975,
"children": {
"SubprocessEnvManager._take_step": {
"total": 403.09487148790924,
"count": 231764,
"self": 15.730115935912181,
"children": {
"TorchPolicy.evaluate": {
"total": 387.36475555199706,
"count": 222955,
"self": 387.36475555199706
}
}
},
"workers": {
"total": 2.7036043450045213,
"count": 231764,
"self": 0.0,
"children": {
"worker_root": {
"total": 2423.845385890985,
"count": 231764,
"is_parallel": true,
"self": 1209.6661248838343,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008195489999707206,
"count": 1,
"is_parallel": true,
"self": 0.00022025999999186752,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005992889999788531,
"count": 2,
"is_parallel": true,
"self": 0.0005992889999788531
}
}
},
"UnityEnvironment.step": {
"total": 0.028301096000006964,
"count": 1,
"is_parallel": true,
"self": 0.0004003730000476935,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019749099999444297,
"count": 1,
"is_parallel": true,
"self": 0.00019749099999444297
},
"communicator.exchange": {
"total": 0.026972172999990107,
"count": 1,
"is_parallel": true,
"self": 0.026972172999990107
},
"steps_from_proto": {
"total": 0.0007310589999747208,
"count": 1,
"is_parallel": true,
"self": 0.00019269900002427676,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000538359999950444,
"count": 2,
"is_parallel": true,
"self": 0.000538359999950444
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1214.179261007151,
"count": 231763,
"is_parallel": true,
"self": 37.621507121053355,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.59798749804406,
"count": 231763,
"is_parallel": true,
"self": 79.59798749804406
},
"communicator.exchange": {
"total": 1009.5039856049939,
"count": 231763,
"is_parallel": true,
"self": 1009.5039856049939
},
"steps_from_proto": {
"total": 87.45578078305982,
"count": 231763,
"is_parallel": true,
"self": 30.72106411109121,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.73471667196861,
"count": 463526,
"is_parallel": true,
"self": 56.73471667196861
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 515.1601818030038,
"count": 231764,
"self": 6.649837362018445,
"children": {
"process_trajectory": {
"total": 165.19497257198645,
"count": 231764,
"self": 163.87553440098588,
"children": {
"RLTrainer._checkpoint": {
"total": 1.31943817100057,
"count": 10,
"self": 1.31943817100057
}
}
},
"_update_policy": {
"total": 343.31537186899885,
"count": 97,
"self": 276.0904722699964,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.22489959900247,
"count": 2910,
"self": 67.22489959900247
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0789999578264542e-06,
"count": 1,
"self": 1.0789999578264542e-06
},
"TrainerController._save_models": {
"total": 0.12102525899990724,
"count": 1,
"self": 0.00215600399997129,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11886925499993595,
"count": 1,
"self": 0.11886925499993595
}
}
}
}
}
}
}