ppo-Huggy / run_logs /timers.json
legalaspro's picture
Huggy
ea07f0f verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3804458379745483,
"min": 1.3804458379745483,
"max": 1.4215736389160156,
"count": 60
},
"Huggy.Policy.Entropy.sum": {
"value": 70239.84375,
"min": 67526.2890625,
"max": 77451.3359375,
"count": 60
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 98.31485148514851,
"min": 88.34821428571429,
"max": 447.1517857142857,
"count": 60
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49649.0,
"min": 48812.0,
"max": 50133.0,
"count": 60
},
"Huggy.Step.mean": {
"value": 2999479.0,
"min": 49749.0,
"max": 2999479.0,
"count": 60
},
"Huggy.Step.sum": {
"value": 2999479.0,
"min": 49749.0,
"max": 2999479.0,
"count": 60
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3580973148345947,
"min": 0.036438342183828354,
"max": 2.4295308589935303,
"count": 60
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1190.839111328125,
"min": 4.044655799865723,
"max": 1299.747802734375,
"count": 60
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.5494548730330893,
"min": 1.6166541140090238,
"max": 3.972915584342325,
"count": 60
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1792.47471088171,
"min": 179.44860665500164,
"max": 2169.8267478346825,
"count": 60
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.5494548730330893,
"min": 1.6166541140090238,
"max": 3.972915584342325,
"count": 60
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1792.47471088171,
"min": 179.44860665500164,
"max": 2169.8267478346825,
"count": 60
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 60
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 60
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.011700202270779603,
"min": 0.00900723785996282,
"max": 0.015729527000221424,
"count": 48
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.011700202270779603,
"min": 0.00900723785996282,
"max": 0.015729527000221424,
"count": 48
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05095967883865039,
"min": 0.020325829510887464,
"max": 0.05095967883865039,
"count": 48
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.05095967883865039,
"min": 0.020325829510887464,
"max": 0.05095967883865039,
"count": 48
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.583998472033342e-06,
"min": 4.583998472033342e-06,
"max": 0.00029383200205599985,
"count": 48
},
"Huggy.Policy.LearningRate.sum": {
"value": 4.583998472033342e-06,
"min": 4.583998472033342e-06,
"max": 0.00029383200205599985,
"count": 48
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10152796666666666,
"min": 0.10152796666666666,
"max": 0.197944,
"count": 48
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.10152796666666666,
"min": 0.10152796666666666,
"max": 0.197944,
"count": 48
},
"Huggy.Policy.Beta.mean": {
"value": 8.624553666666679e-05,
"min": 8.624553666666679e-05,
"max": 0.004897405600000002,
"count": 48
},
"Huggy.Policy.Beta.sum": {
"value": 8.624553666666679e-05,
"min": 8.624553666666679e-05,
"max": 0.004897405600000002,
"count": 48
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1730735926",
"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=Huggy3 --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": "1730739278"
},
"total": 3352.0195238860006,
"count": 1,
"self": 0.32168215600086114,
"children": {
"run_training.setup": {
"total": 0.05849840199971368,
"count": 1,
"self": 0.05849840199971368
},
"TrainerController.start_learning": {
"total": 3351.639343328,
"count": 1,
"self": 6.42968809166814,
"children": {
"TrainerController._reset_env": {
"total": 1.9763992649995998,
"count": 1,
"self": 1.9763992649995998
},
"TrainerController.advance": {
"total": 3343.1023010693334,
"count": 346244,
"self": 5.913388387607483,
"children": {
"env_step": {
"total": 2378.616213645988,
"count": 346244,
"self": 1802.2615034367436,
"children": {
"SubprocessEnvManager._take_step": {
"total": 572.3139085806733,
"count": 346244,
"self": 21.671261441225397,
"children": {
"TorchPolicy.evaluate": {
"total": 550.642647139448,
"count": 334292,
"self": 550.642647139448
}
}
},
"workers": {
"total": 4.040801628570989,
"count": 346244,
"self": 0.0,
"children": {
"worker_root": {
"total": 3340.9970179501197,
"count": 346244,
"is_parallel": true,
"self": 1890.5932259452075,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008735420005905326,
"count": 1,
"is_parallel": true,
"self": 0.0002642150011524791,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006093269994380535,
"count": 2,
"is_parallel": true,
"self": 0.0006093269994380535
}
}
},
"UnityEnvironment.step": {
"total": 0.021068762999675528,
"count": 1,
"is_parallel": true,
"self": 0.0003229260000807699,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00016661999961797846,
"count": 1,
"is_parallel": true,
"self": 0.00016661999961797846
},
"communicator.exchange": {
"total": 0.020067968999683217,
"count": 1,
"is_parallel": true,
"self": 0.020067968999683217
},
"steps_from_proto": {
"total": 0.0005112480002935627,
"count": 1,
"is_parallel": true,
"self": 0.00016482499995618127,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0003464230003373814,
"count": 2,
"is_parallel": true,
"self": 0.0003464230003373814
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1450.4037920049122,
"count": 346243,
"is_parallel": true,
"self": 39.693915219837436,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 75.67559444013114,
"count": 346243,
"is_parallel": true,
"self": 75.67559444013114
},
"communicator.exchange": {
"total": 1243.948104283062,
"count": 346243,
"is_parallel": true,
"self": 1243.948104283062
},
"steps_from_proto": {
"total": 91.08617806188158,
"count": 346243,
"is_parallel": true,
"self": 34.960538926589834,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.12563913529175,
"count": 692486,
"is_parallel": true,
"self": 56.12563913529175
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 958.572699035738,
"count": 346244,
"self": 9.520970072259843,
"children": {
"process_trajectory": {
"total": 218.84396512347212,
"count": 346244,
"self": 215.3858673074683,
"children": {
"RLTrainer._checkpoint": {
"total": 3.4580978160038285,
"count": 30,
"self": 3.4580978160038285
}
}
},
"_update_policy": {
"total": 730.207763840006,
"count": 48,
"self": 625.0683427559998,
"children": {
"TorchPPOOptimizer.update": {
"total": 105.13942108400624,
"count": 3600,
"self": 105.13942108400624
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.849991329247132e-07,
"count": 1,
"self": 9.849991329247132e-07
},
"TrainerController._save_models": {
"total": 0.13095391699971515,
"count": 1,
"self": 0.0025618249983381247,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12839209200137702,
"count": 1,
"self": 0.12839209200137702
}
}
}
}
}
}
}