ppo-Huggy / run_logs /timers.json
niratpatel's picture
Huggy
3a9896b verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4043514728546143,
"min": 1.4043514728546143,
"max": 1.4272494316101074,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70008.328125,
"min": 69054.65625,
"max": 77768.65625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 85.28497409326425,
"min": 76.87071651090342,
"max": 412.495867768595,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49380.0,
"min": 48797.0,
"max": 50031.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999939.0,
"min": 49886.0,
"max": 1999939.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999939.0,
"min": 49886.0,
"max": 1999939.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4554221630096436,
"min": 0.04607437923550606,
"max": 2.496825695037842,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1421.689453125,
"min": 5.52892541885376,
"max": 1534.26416015625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9192997104969254,
"min": 1.717602771272262,
"max": 4.09575582693394,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2269.27453237772,
"min": 206.11233255267143,
"max": 2477.4953458309174,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9192997104969254,
"min": 1.717602771272262,
"max": 4.09575582693394,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2269.27453237772,
"min": 206.11233255267143,
"max": 2477.4953458309174,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015892483313412715,
"min": 0.01383258375620547,
"max": 0.020557245069964362,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04767744994023815,
"min": 0.02766516751241094,
"max": 0.05998445776252387,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.052913555709852116,
"min": 0.02249135465050737,
"max": 0.06180795431137085,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15874066712955634,
"min": 0.04498270930101474,
"max": 0.18186167031526568,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5397488201166714e-06,
"min": 3.5397488201166714e-06,
"max": 0.000295335976554675,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0619246460350014e-05,
"min": 1.0619246460350014e-05,
"max": 0.0008442814685728498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10117988333333335,
"min": 0.10117988333333335,
"max": 0.19844532500000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30353965000000005,
"min": 0.20752450000000006,
"max": 0.58142715,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.887617833333343e-05,
"min": 6.887617833333343e-05,
"max": 0.0049224217175,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002066285350000003,
"min": 0.0002066285350000003,
"max": 0.014073214785,
"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": "1745430142",
"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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1745432594"
},
"total": 2451.989284545,
"count": 1,
"self": 0.5121991560004062,
"children": {
"run_training.setup": {
"total": 0.02302379100001417,
"count": 1,
"self": 0.02302379100001417
},
"TrainerController.start_learning": {
"total": 2451.4540615979995,
"count": 1,
"self": 4.350304361998042,
"children": {
"TrainerController._reset_env": {
"total": 3.7663043649999963,
"count": 1,
"self": 3.7663043649999963
},
"TrainerController.advance": {
"total": 2443.2114176410014,
"count": 232580,
"self": 4.352926803093851,
"children": {
"env_step": {
"total": 1914.8459892609271,
"count": 232580,
"self": 1507.7150680779698,
"children": {
"SubprocessEnvManager._take_step": {
"total": 404.5597930109245,
"count": 232580,
"self": 15.669440462843454,
"children": {
"TorchPolicy.evaluate": {
"total": 388.89035254808107,
"count": 222900,
"self": 388.89035254808107
}
}
},
"workers": {
"total": 2.571128172032786,
"count": 232580,
"self": 0.0,
"children": {
"worker_root": {
"total": 2443.9159877710367,
"count": 232580,
"is_parallel": true,
"self": 1213.0058024931204,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010557020000305783,
"count": 1,
"is_parallel": true,
"self": 0.00032027200018092117,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007354299998496572,
"count": 2,
"is_parallel": true,
"self": 0.0007354299998496572
}
}
},
"UnityEnvironment.step": {
"total": 0.035512888999960524,
"count": 1,
"is_parallel": true,
"self": 0.0003124290000187102,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018591200000628305,
"count": 1,
"is_parallel": true,
"self": 0.00018591200000628305
},
"communicator.exchange": {
"total": 0.03433588999996573,
"count": 1,
"is_parallel": true,
"self": 0.03433588999996573
},
"steps_from_proto": {
"total": 0.0006786579999698006,
"count": 1,
"is_parallel": true,
"self": 0.00018525199993746355,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000493406000032337,
"count": 2,
"is_parallel": true,
"self": 0.000493406000032337
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1230.9101852779163,
"count": 232579,
"is_parallel": true,
"self": 37.331470336963775,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.91938775295341,
"count": 232579,
"is_parallel": true,
"self": 79.91938775295341
},
"communicator.exchange": {
"total": 1027.1955432779728,
"count": 232579,
"is_parallel": true,
"self": 1027.1955432779728
},
"steps_from_proto": {
"total": 86.46378391002656,
"count": 232579,
"is_parallel": true,
"self": 30.504550282080913,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.95923362794565,
"count": 465158,
"is_parallel": true,
"self": 55.95923362794565
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 524.0125015769803,
"count": 232580,
"self": 6.437681115934538,
"children": {
"process_trajectory": {
"total": 162.55456432304493,
"count": 232580,
"self": 161.32180379004478,
"children": {
"RLTrainer._checkpoint": {
"total": 1.232760533000146,
"count": 10,
"self": 1.232760533000146
}
}
},
"_update_policy": {
"total": 355.02025613800083,
"count": 97,
"self": 287.8547217219856,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.16553441601525,
"count": 2910,
"self": 67.16553441601525
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.480001270072535e-07,
"count": 1,
"self": 8.480001270072535e-07
},
"TrainerController._save_models": {
"total": 0.12603438199994343,
"count": 1,
"self": 0.002204067000093346,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12383031499985009,
"count": 1,
"self": 0.12383031499985009
}
}
}
}
}
}
}