ppo-Huggy / run_logs /timers.json
r-s-s's picture
Huggy
41f6397 verified
raw
history blame
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4012099504470825,
"min": 1.4012099504470825,
"max": 1.4253830909729004,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70183.8046875,
"min": 69177.578125,
"max": 76316.3984375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 80.38056013179572,
"min": 72.30058651026393,
"max": 381.5681818181818,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 48791.0,
"min": 48791.0,
"max": 50367.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999982.0,
"min": 49749.0,
"max": 1999982.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999982.0,
"min": 49749.0,
"max": 1999982.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4593958854675293,
"min": 0.0034036964643746614,
"max": 2.5142109394073486,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1492.853271484375,
"min": 0.44588422775268555,
"max": 1670.667236328125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.821571289118275,
"min": 1.7875859307423803,
"max": 4.0350967209888156,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2319.693772494793,
"min": 234.17375692725182,
"max": 2638.5745356082916,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.821571289118275,
"min": 1.7875859307423803,
"max": 4.0350967209888156,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2319.693772494793,
"min": 234.17375692725182,
"max": 2638.5745356082916,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016540741185821793,
"min": 0.01386554249523518,
"max": 0.019552061780511092,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04962222355746538,
"min": 0.02773108499047036,
"max": 0.05865618534153327,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05325023689203792,
"min": 0.02315174484004577,
"max": 0.06416384681231446,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15975071067611377,
"min": 0.04630348968009154,
"max": 0.1924915404369434,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.751448749549986e-06,
"min": 3.751448749549986e-06,
"max": 0.00029534235155254996,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1254346248649958e-05,
"min": 1.1254346248649958e-05,
"max": 0.0008438578687140501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10125045,
"min": 0.10125045,
"max": 0.19844744999999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30375135000000003,
"min": 0.20766185,
"max": 0.58128595,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.239745499999977e-05,
"min": 7.239745499999977e-05,
"max": 0.004922527755000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002171923649999993,
"min": 0.0002171923649999993,
"max": 0.014066168905,
"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": "1723927062",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1723929568"
},
"total": 2506.196089672,
"count": 1,
"self": 0.6402836100005516,
"children": {
"run_training.setup": {
"total": 0.056978283000034935,
"count": 1,
"self": 0.056978283000034935
},
"TrainerController.start_learning": {
"total": 2505.498827779,
"count": 1,
"self": 4.599098134009182,
"children": {
"TrainerController._reset_env": {
"total": 2.991325827999958,
"count": 1,
"self": 2.991325827999958
},
"TrainerController.advance": {
"total": 2497.743514796991,
"count": 233182,
"self": 4.888519111795631,
"children": {
"env_step": {
"total": 1974.8664876661114,
"count": 233182,
"self": 1625.1053789468683,
"children": {
"SubprocessEnvManager._take_step": {
"total": 346.68656938811887,
"count": 233182,
"self": 16.8553882291925,
"children": {
"TorchPolicy.evaluate": {
"total": 329.83118115892637,
"count": 222995,
"self": 329.83118115892637
}
}
},
"workers": {
"total": 3.074539331124356,
"count": 233182,
"self": 0.0,
"children": {
"worker_root": {
"total": 2497.9386212780178,
"count": 233182,
"is_parallel": true,
"self": 1188.853624617926,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010195410000051197,
"count": 1,
"is_parallel": true,
"self": 0.00027506999992965575,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000744471000075464,
"count": 2,
"is_parallel": true,
"self": 0.000744471000075464
}
}
},
"UnityEnvironment.step": {
"total": 0.05073751700001594,
"count": 1,
"is_parallel": true,
"self": 0.00038024900004529627,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00025481299996954476,
"count": 1,
"is_parallel": true,
"self": 0.00025481299996954476
},
"communicator.exchange": {
"total": 0.04933687499999451,
"count": 1,
"is_parallel": true,
"self": 0.04933687499999451
},
"steps_from_proto": {
"total": 0.0007655800000065938,
"count": 1,
"is_parallel": true,
"self": 0.00019730499991510442,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005682750000914893,
"count": 2,
"is_parallel": true,
"self": 0.0005682750000914893
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1309.0849966600917,
"count": 233181,
"is_parallel": true,
"self": 39.26669921408484,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.69457237811685,
"count": 233181,
"is_parallel": true,
"self": 83.69457237811685
},
"communicator.exchange": {
"total": 1092.6665856409104,
"count": 233181,
"is_parallel": true,
"self": 1092.6665856409104
},
"steps_from_proto": {
"total": 93.45713942697978,
"count": 233181,
"is_parallel": true,
"self": 35.33691441190206,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.12022501507772,
"count": 466362,
"is_parallel": true,
"self": 58.12022501507772
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 517.9885080190838,
"count": 233182,
"self": 6.727999988164356,
"children": {
"process_trajectory": {
"total": 166.79510624092086,
"count": 233182,
"self": 165.43911647692084,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3559897640000145,
"count": 10,
"self": 1.3559897640000145
}
}
},
"_update_policy": {
"total": 344.4654017899986,
"count": 97,
"self": 279.5585085660142,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.90689322398441,
"count": 2910,
"self": 64.90689322398441
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5800001165189315e-06,
"count": 1,
"self": 1.5800001165189315e-06
},
"TrainerController._save_models": {
"total": 0.16488743999980215,
"count": 1,
"self": 0.0028004629998577,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16208697699994445,
"count": 1,
"self": 0.16208697699994445
}
}
}
}
}
}
}