ppo-Huggy / run_logs /timers.json
Sylvain Lapeyrade
Huggy
cfb2f0e verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4035899639129639,
"min": 1.4035899639129639,
"max": 1.4266440868377686,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70875.6796875,
"min": 69089.3203125,
"max": 76636.5859375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 75.96615384615384,
"min": 72.49706744868035,
"max": 417.2396694214876,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49378.0,
"min": 49031.0,
"max": 50486.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999951.0,
"min": 49918.0,
"max": 1999951.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999951.0,
"min": 49918.0,
"max": 1999951.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5728836059570312,
"min": 0.03174003213644028,
"max": 2.5728836059570312,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1672.374267578125,
"min": 3.8088040351867676,
"max": 1683.669189453125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 4.002081578144661,
"min": 1.8594467733055353,
"max": 4.002081578144661,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2601.3530257940292,
"min": 223.13361279666424,
"max": 2601.3530257940292,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 4.002081578144661,
"min": 1.8594467733055353,
"max": 4.002081578144661,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2601.3530257940292,
"min": 223.13361279666424,
"max": 2601.3530257940292,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.0171087722449253,
"min": 0.013642374844574888,
"max": 0.02175537795216466,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.051326316734775904,
"min": 0.02843004867742517,
"max": 0.06237788660995042,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06343470352391402,
"min": 0.02312822286039591,
"max": 0.0666302224000295,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.19030411057174207,
"min": 0.04625644572079182,
"max": 0.19404803899427253,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.935998688033336e-06,
"min": 3.935998688033336e-06,
"max": 0.0002953116765627749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.180799606410001e-05,
"min": 1.180799606410001e-05,
"max": 0.0008443432685522499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10131196666666668,
"min": 0.10131196666666668,
"max": 0.19843722500000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30393590000000004,
"min": 0.2077566500000001,
"max": 0.5814477499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.546713666666673e-05,
"min": 7.546713666666673e-05,
"max": 0.004922017527499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022640141000000017,
"min": 0.00022640141000000017,
"max": 0.014074242725,
"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": "1744634131",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1744636688"
},
"total": 2556.9107729310003,
"count": 1,
"self": 0.5322935730000609,
"children": {
"run_training.setup": {
"total": 0.0237065530000109,
"count": 1,
"self": 0.0237065530000109
},
"TrainerController.start_learning": {
"total": 2556.3547728050003,
"count": 1,
"self": 4.606289275924155,
"children": {
"TrainerController._reset_env": {
"total": 3.0811601719999544,
"count": 1,
"self": 3.0811601719999544
},
"TrainerController.advance": {
"total": 2548.487511607077,
"count": 233299,
"self": 4.838802694825972,
"children": {
"env_step": {
"total": 2051.7660742480657,
"count": 233299,
"self": 1602.7107632311272,
"children": {
"SubprocessEnvManager._take_step": {
"total": 446.1689917699091,
"count": 233299,
"self": 16.61699593705248,
"children": {
"TorchPolicy.evaluate": {
"total": 429.5519958328566,
"count": 222950,
"self": 429.5519958328566
}
}
},
"workers": {
"total": 2.8863192470294052,
"count": 233299,
"self": 0.0,
"children": {
"worker_root": {
"total": 2548.54349008181,
"count": 233299,
"is_parallel": true,
"self": 1242.9955201529008,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010749969999324094,
"count": 1,
"is_parallel": true,
"self": 0.00041656300004433433,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000658433999888075,
"count": 2,
"is_parallel": true,
"self": 0.000658433999888075
}
}
},
"UnityEnvironment.step": {
"total": 0.03980245200000354,
"count": 1,
"is_parallel": true,
"self": 0.00037550499996541475,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019809700006589992,
"count": 1,
"is_parallel": true,
"self": 0.00019809700006589992
},
"communicator.exchange": {
"total": 0.038460041999996974,
"count": 1,
"is_parallel": true,
"self": 0.038460041999996974
},
"steps_from_proto": {
"total": 0.0007688079999752517,
"count": 1,
"is_parallel": true,
"self": 0.00020505099996626086,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005637570000089909,
"count": 2,
"is_parallel": true,
"self": 0.0005637570000089909
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1305.5479699289092,
"count": 233298,
"is_parallel": true,
"self": 39.02820576889917,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.69561647789328,
"count": 233298,
"is_parallel": true,
"self": 86.69561647789328
},
"communicator.exchange": {
"total": 1089.862012247115,
"count": 233298,
"is_parallel": true,
"self": 1089.862012247115
},
"steps_from_proto": {
"total": 89.96213543500176,
"count": 233298,
"is_parallel": true,
"self": 33.711921048926115,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.25021438607564,
"count": 466596,
"is_parallel": true,
"self": 56.25021438607564
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 491.88263466418516,
"count": 233299,
"self": 6.725666513345232,
"children": {
"process_trajectory": {
"total": 177.52490322184212,
"count": 233299,
"self": 176.15871221884254,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3661910029995852,
"count": 10,
"self": 1.3661910029995852
}
}
},
"_update_policy": {
"total": 307.6320649289978,
"count": 97,
"self": 242.545397859996,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.0866670690018,
"count": 2910,
"self": 65.0866670690018
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.6099993445095606e-06,
"count": 1,
"self": 1.6099993445095606e-06
},
"TrainerController._save_models": {
"total": 0.1798101399999723,
"count": 1,
"self": 0.002821424000103434,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17698871599986887,
"count": 1,
"self": 0.17698871599986887
}
}
}
}
}
}
}