ppo-Huggy / run_logs /timers.json
bittoby's picture
Huggy
263b74b verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4030195474624634,
"min": 1.4030195474624634,
"max": 1.428842306137085,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70874.9375,
"min": 67786.9296875,
"max": 75039.9765625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 88.46332737030411,
"min": 79.23434991974318,
"max": 369.3703703703704,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49451.0,
"min": 49180.0,
"max": 49964.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999271.0,
"min": 49611.0,
"max": 1999271.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999271.0,
"min": 49611.0,
"max": 1999271.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.426896333694458,
"min": 0.11408145725727081,
"max": 2.507927417755127,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1356.635009765625,
"min": 15.286914825439453,
"max": 1559.382080078125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.686092944499205,
"min": 1.8897129868838325,
"max": 3.9215332741587474,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2060.5259559750557,
"min": 253.22154024243355,
"max": 2433.4563893079758,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.686092944499205,
"min": 1.8897129868838325,
"max": 3.9215332741587474,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2060.5259559750557,
"min": 253.22154024243355,
"max": 2433.4563893079758,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018960492238127496,
"min": 0.013081660444731823,
"max": 0.02061250276528881,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.056881476714382484,
"min": 0.026163320889463645,
"max": 0.06183750829586643,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06338192377653387,
"min": 0.02155718971043825,
"max": 0.06338192377653387,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.19014577132960161,
"min": 0.0431143794208765,
"max": 0.19014577132960161,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5872988042666683e-06,
"min": 3.5872988042666683e-06,
"max": 0.00029537865154045,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0761896412800004e-05,
"min": 1.0761896412800004e-05,
"max": 0.0008443029185657,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10119573333333333,
"min": 0.10119573333333333,
"max": 0.19845954999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3035872,
"min": 0.20753945000000001,
"max": 0.5814343000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.966709333333335e-05,
"min": 6.966709333333335e-05,
"max": 0.004923131545000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020900128000000007,
"min": 0.00020900128000000007,
"max": 0.01407357157,
"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": "1766413994",
"python_version": "3.10.12 (main, Nov 4 2025, 08:48:33) [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=Huggy --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1766417003"
},
"total": 3008.4399569789994,
"count": 1,
"self": 0.8550145739991422,
"children": {
"run_training.setup": {
"total": 0.032072455000161426,
"count": 1,
"self": 0.032072455000161426
},
"TrainerController.start_learning": {
"total": 3007.55286995,
"count": 1,
"self": 5.905111663184471,
"children": {
"TrainerController._reset_env": {
"total": 3.5637167620000127,
"count": 1,
"self": 3.5637167620000127
},
"TrainerController.advance": {
"total": 2997.9178486508154,
"count": 232688,
"self": 5.5495252256910135,
"children": {
"env_step": {
"total": 2450.0910307330864,
"count": 232688,
"self": 1977.7584741171381,
"children": {
"SubprocessEnvManager._take_step": {
"total": 468.6401643199058,
"count": 232688,
"self": 18.73896722677614,
"children": {
"TorchPolicy.evaluate": {
"total": 449.90119709312967,
"count": 222964,
"self": 449.90119709312967
}
}
},
"workers": {
"total": 3.692392296042499,
"count": 232688,
"self": 0.0,
"children": {
"worker_root": {
"total": 2992.220750970095,
"count": 232688,
"is_parallel": true,
"self": 1394.050097105947,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009020099998906517,
"count": 1,
"is_parallel": true,
"self": 0.0002559219999511697,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000646087999939482,
"count": 2,
"is_parallel": true,
"self": 0.000646087999939482
}
}
},
"UnityEnvironment.step": {
"total": 0.030953276999980517,
"count": 1,
"is_parallel": true,
"self": 0.00037018700004409766,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023222499999064894,
"count": 1,
"is_parallel": true,
"self": 0.00023222499999064894
},
"communicator.exchange": {
"total": 0.029502222000019174,
"count": 1,
"is_parallel": true,
"self": 0.029502222000019174
},
"steps_from_proto": {
"total": 0.0008486429999265965,
"count": 1,
"is_parallel": true,
"self": 0.00025535399981890805,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005932890001076885,
"count": 2,
"is_parallel": true,
"self": 0.0005932890001076885
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1598.170653864148,
"count": 232687,
"is_parallel": true,
"self": 45.390814673973864,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 92.16356163105047,
"count": 232687,
"is_parallel": true,
"self": 92.16356163105047
},
"communicator.exchange": {
"total": 1352.1120529010516,
"count": 232687,
"is_parallel": true,
"self": 1352.1120529010516
},
"steps_from_proto": {
"total": 108.50422465807219,
"count": 232687,
"is_parallel": true,
"self": 36.907528690904655,
"children": {
"_process_rank_one_or_two_observation": {
"total": 71.59669596716753,
"count": 465374,
"is_parallel": true,
"self": 71.59669596716753
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 542.2772926920379,
"count": 232688,
"self": 8.804529689173478,
"children": {
"process_trajectory": {
"total": 177.9177542778625,
"count": 232688,
"self": 176.67026571486258,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2474885629999335,
"count": 10,
"self": 1.2474885629999335
}
}
},
"_update_policy": {
"total": 355.5550087250019,
"count": 97,
"self": 285.56064945599064,
"children": {
"TorchPPOOptimizer.update": {
"total": 69.99435926901128,
"count": 2910,
"self": 69.99435926901128
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2760001482092775e-06,
"count": 1,
"self": 1.2760001482092775e-06
},
"TrainerController._save_models": {
"total": 0.16619159800029593,
"count": 1,
"self": 0.002326895000805962,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16386470299948996,
"count": 1,
"self": 0.16386470299948996
}
}
}
}
}
}
}