ppo-Huggy / run_logs /timers.json
jaturken's picture
Huggy
973801d verified
raw
history blame
17.5 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4111082553863525,
"min": 1.4111082553863525,
"max": 1.4290592670440674,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71383.734375,
"min": 68530.6484375,
"max": 76990.28125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 90.60366972477064,
"min": 81.25986842105263,
"max": 406.5934959349593,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49379.0,
"min": 48850.0,
"max": 50011.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999877.0,
"min": 49901.0,
"max": 1999877.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999877.0,
"min": 49901.0,
"max": 1999877.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.419201374053955,
"min": 0.005079266149550676,
"max": 2.4943931102752686,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1318.4647216796875,
"min": 0.6196704506874084,
"max": 1449.1875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.804456990574478,
"min": 1.8827808855986985,
"max": 3.9675122069564845,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2073.4290598630905,
"min": 229.69926804304123,
"max": 2353.4935162067413,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.804456990574478,
"min": 1.8827808855986985,
"max": 3.9675122069564845,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2073.4290598630905,
"min": 229.69926804304123,
"max": 2353.4935162067413,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016258050145754373,
"min": 0.012755578335115085,
"max": 0.02071335265354719,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04877415043726312,
"min": 0.02551115667023017,
"max": 0.05708454569394235,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05507121380004618,
"min": 0.022565718336651722,
"max": 0.05697398154685895,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16521364140013856,
"min": 0.045131436673303445,
"max": 0.17035252576073012,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3733988755666684e-06,
"min": 3.3733988755666684e-06,
"max": 0.0002952497265834249,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0120196626700005e-05,
"min": 1.0120196626700005e-05,
"max": 0.0008437260187580001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10112443333333332,
"min": 0.10112443333333332,
"max": 0.19841657499999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30337329999999996,
"min": 0.20738524999999997,
"max": 0.5812419999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.610922333333335e-05,
"min": 6.610922333333335e-05,
"max": 0.004920987092499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019832767000000007,
"min": 0.00019832767000000007,
"max": 0.014063975800000003,
"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": "1734707461",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/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": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1734710236"
},
"total": 2774.8771800349996,
"count": 1,
"self": 0.4796660799993333,
"children": {
"run_training.setup": {
"total": 0.06017516099996101,
"count": 1,
"self": 0.06017516099996101
},
"TrainerController.start_learning": {
"total": 2774.337338794,
"count": 1,
"self": 4.9292996559747735,
"children": {
"TrainerController._reset_env": {
"total": 5.42502770100009,
"count": 1,
"self": 5.42502770100009
},
"TrainerController.advance": {
"total": 2763.8451935070248,
"count": 232223,
"self": 5.172522394904718,
"children": {
"env_step": {
"total": 2204.631656765066,
"count": 232223,
"self": 1709.508302484055,
"children": {
"SubprocessEnvManager._take_step": {
"total": 491.92305354792734,
"count": 232223,
"self": 17.187514434917603,
"children": {
"TorchPolicy.evaluate": {
"total": 474.73553911300974,
"count": 223020,
"self": 474.73553911300974
}
}
},
"workers": {
"total": 3.2003007330836226,
"count": 232223,
"self": 0.0,
"children": {
"worker_root": {
"total": 2766.432508051022,
"count": 232223,
"is_parallel": true,
"self": 1383.827925803005,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001086542999928497,
"count": 1,
"is_parallel": true,
"self": 0.00033217400005014497,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000754368999878352,
"count": 2,
"is_parallel": true,
"self": 0.000754368999878352
}
}
},
"UnityEnvironment.step": {
"total": 0.052085536000049615,
"count": 1,
"is_parallel": true,
"self": 0.0004617189999862603,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023046199999043893,
"count": 1,
"is_parallel": true,
"self": 0.00023046199999043893
},
"communicator.exchange": {
"total": 0.05053649499996027,
"count": 1,
"is_parallel": true,
"self": 0.05053649499996027
},
"steps_from_proto": {
"total": 0.000856860000112647,
"count": 1,
"is_parallel": true,
"self": 0.00024089500016089005,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006159649999517569,
"count": 2,
"is_parallel": true,
"self": 0.0006159649999517569
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1382.604582248017,
"count": 232222,
"is_parallel": true,
"self": 40.393095346184055,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 95.43018510997058,
"count": 232222,
"is_parallel": true,
"self": 95.43018510997058
},
"communicator.exchange": {
"total": 1147.6798055499153,
"count": 232222,
"is_parallel": true,
"self": 1147.6798055499153
},
"steps_from_proto": {
"total": 99.10149624194719,
"count": 232222,
"is_parallel": true,
"self": 38.52340885990907,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.57808738203812,
"count": 464444,
"is_parallel": true,
"self": 60.57808738203812
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 554.0410143470542,
"count": 232223,
"self": 7.220232088990997,
"children": {
"process_trajectory": {
"total": 194.53379831106304,
"count": 232223,
"self": 192.82453799206314,
"children": {
"RLTrainer._checkpoint": {
"total": 1.7092603189998954,
"count": 10,
"self": 1.7092603189998954
}
}
},
"_update_policy": {
"total": 352.2869839470002,
"count": 97,
"self": 284.54264789599074,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.74433605100944,
"count": 2910,
"self": 67.74433605100944
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.590003173798323e-07,
"count": 1,
"self": 9.590003173798323e-07
},
"TrainerController._save_models": {
"total": 0.13781697100012025,
"count": 1,
"self": 0.0025136409999504394,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1353033300001698,
"count": 1,
"self": 0.1353033300001698
}
}
}
}
}
}
}