ppo-Huggy / run_logs /timers.json
PrMoriarty's picture
Huggy
d8ad32c verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4030263423919678,
"min": 1.4030263423919678,
"max": 1.426921010017395,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68616.40625,
"min": 68332.2734375,
"max": 78442.328125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 81.43894389438944,
"min": 81.43894389438944,
"max": 390.953125,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49352.0,
"min": 48762.0,
"max": 50042.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999999.0,
"min": 49505.0,
"max": 1999999.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999999.0,
"min": 49505.0,
"max": 1999999.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.42225980758667,
"min": -0.02712833695113659,
"max": 2.480205774307251,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1470.311767578125,
"min": -3.445298910140991,
"max": 1470.7620849609375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7419360413582754,
"min": 1.8798750134434288,
"max": 3.95192750037018,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2271.355177104473,
"min": 238.74412670731544,
"max": 2343.4930077195168,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7419360413582754,
"min": 1.8798750134434288,
"max": 3.95192750037018,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2271.355177104473,
"min": 238.74412670731544,
"max": 2343.4930077195168,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018039913827225165,
"min": 0.01325698136157977,
"max": 0.020264596676214653,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0541197414816755,
"min": 0.02651396272315954,
"max": 0.060793790028643956,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06111374104188547,
"min": 0.02379726755122344,
"max": 0.06111374104188547,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18334122312565643,
"min": 0.04759453510244688,
"max": 0.18334122312565643,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5953988015666685e-06,
"min": 3.5953988015666685e-06,
"max": 0.00029532397655867497,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0786196404700005e-05,
"min": 1.0786196404700005e-05,
"max": 0.0008441218686260501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10119843333333334,
"min": 0.10119843333333334,
"max": 0.198441325,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3035953,
"min": 0.20753020000000008,
"max": 0.5813739499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.980182333333337e-05,
"min": 6.980182333333337e-05,
"max": 0.0049222221175,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020940547000000012,
"min": 0.00020940547000000012,
"max": 0.014070560104999998,
"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": "1746009901",
"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": "1746012511"
},
"total": 2609.703603932,
"count": 1,
"self": 0.44292791899988515,
"children": {
"run_training.setup": {
"total": 0.023095304999969812,
"count": 1,
"self": 0.023095304999969812
},
"TrainerController.start_learning": {
"total": 2609.237580708,
"count": 1,
"self": 4.707127914965895,
"children": {
"TrainerController._reset_env": {
"total": 3.3623949369999764,
"count": 1,
"self": 3.3623949369999764
},
"TrainerController.advance": {
"total": 2601.0591848730346,
"count": 232239,
"self": 4.999162071002502,
"children": {
"env_step": {
"total": 2103.002623744103,
"count": 232239,
"self": 1648.6826538220023,
"children": {
"SubprocessEnvManager._take_step": {
"total": 451.3504895740707,
"count": 232239,
"self": 16.863444201017387,
"children": {
"TorchPolicy.evaluate": {
"total": 434.4870453730533,
"count": 222862,
"self": 434.4870453730533
}
}
},
"workers": {
"total": 2.969480348029947,
"count": 232239,
"self": 0.0,
"children": {
"worker_root": {
"total": 2601.2790914710035,
"count": 232239,
"is_parallel": true,
"self": 1260.4818406490144,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011832679999770335,
"count": 1,
"is_parallel": true,
"self": 0.0003338159999657364,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008494520000112971,
"count": 2,
"is_parallel": true,
"self": 0.0008494520000112971
}
}
},
"UnityEnvironment.step": {
"total": 0.032778321000023425,
"count": 1,
"is_parallel": true,
"self": 0.00039224700003615,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001924690000123519,
"count": 1,
"is_parallel": true,
"self": 0.0001924690000123519
},
"communicator.exchange": {
"total": 0.031414326999993136,
"count": 1,
"is_parallel": true,
"self": 0.031414326999993136
},
"steps_from_proto": {
"total": 0.0007792779999817867,
"count": 1,
"is_parallel": true,
"self": 0.00022277299990491883,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005565050000768679,
"count": 2,
"is_parallel": true,
"self": 0.0005565050000768679
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1340.797250821989,
"count": 232238,
"is_parallel": true,
"self": 39.28392112776555,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 88.21399696104481,
"count": 232238,
"is_parallel": true,
"self": 88.21399696104481
},
"communicator.exchange": {
"total": 1120.5100640410583,
"count": 232238,
"is_parallel": true,
"self": 1120.5100640410583
},
"steps_from_proto": {
"total": 92.78926869212046,
"count": 232238,
"is_parallel": true,
"self": 34.89499420205334,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.89427449006712,
"count": 464476,
"is_parallel": true,
"self": 57.89427449006712
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 493.05739905792893,
"count": 232239,
"self": 7.292894231974742,
"children": {
"process_trajectory": {
"total": 177.09800787095423,
"count": 232239,
"self": 175.77137480495435,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3266330659998857,
"count": 10,
"self": 1.3266330659998857
}
}
},
"_update_policy": {
"total": 308.66649695499996,
"count": 97,
"self": 244.00254439699734,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.66395255800262,
"count": 2910,
"self": 64.66395255800262
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2939999578520656e-06,
"count": 1,
"self": 1.2939999578520656e-06
},
"TrainerController._save_models": {
"total": 0.10887168899989774,
"count": 1,
"self": 0.0015880579999247857,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10728363099997296,
"count": 1,
"self": 0.10728363099997296
}
}
}
}
}
}
}