ppo-Huggy / run_logs /timers.json
abkimc's picture
Huggy
4246003 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.1319630146026611,
"min": 1.1319630146026611,
"max": 1.4161220788955688,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 56937.73828125,
"min": 55826.55078125,
"max": 78167.109375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 71.4833091436865,
"min": 69.878223495702,
"max": 384.4580152671756,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49252.0,
"min": 48676.0,
"max": 50364.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999964.0,
"min": 49906.0,
"max": 1999964.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999964.0,
"min": 49906.0,
"max": 1999964.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.282141923904419,
"min": 0.039426546543836594,
"max": 2.2889580726623535,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1574.6778564453125,
"min": 5.12545108795166,
"max": 1583.92236328125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9295589315286583,
"min": 1.9643298499859296,
"max": 4.040680040124729,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2711.395662754774,
"min": 255.36288049817085,
"max": 2732.3139791190624,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9295589315286583,
"min": 1.9643298499859296,
"max": 4.040680040124729,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2711.395662754774,
"min": 255.36288049817085,
"max": 2732.3139791190624,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.023879111877209248,
"min": 0.021484633268119068,
"max": 0.028851617614236602,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.07163733563162775,
"min": 0.042969266536238136,
"max": 0.08257306039449759,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0363263832198249,
"min": 0.018551606643531057,
"max": 0.04073135269184907,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1089791496594747,
"min": 0.037927545529479786,
"max": 0.10972756650298833,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 1.0331098966900018e-05,
"min": 1.0331098966900018e-05,
"max": 0.00098434850156515,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 3.0993296900700056e-05,
"min": 3.0993296900700056e-05,
"max": 0.0028128805187119495,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1010331,
"min": 0.1010331,
"max": 0.19843485,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3030993,
"min": 0.20719725,
"max": 0.5812880500000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.15516900000001e-05,
"min": 6.15516900000001e-05,
"max": 0.004921899014999998,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00018465507000000028,
"min": 0.00018465507000000028,
"max": 0.014066273694999996,
"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": "1746261492",
"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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1746263902"
},
"total": 2410.3238968079995,
"count": 1,
"self": 0.4420507949998864,
"children": {
"run_training.setup": {
"total": 0.02947614499998963,
"count": 1,
"self": 0.02947614499998963
},
"TrainerController.start_learning": {
"total": 2409.8523698679996,
"count": 1,
"self": 4.248592887903669,
"children": {
"TrainerController._reset_env": {
"total": 3.7259423929999684,
"count": 1,
"self": 3.7259423929999684
},
"TrainerController.advance": {
"total": 2401.774345355096,
"count": 233624,
"self": 4.422456056017381,
"children": {
"env_step": {
"total": 1881.0420364970155,
"count": 233624,
"self": 1482.2808417388856,
"children": {
"SubprocessEnvManager._take_step": {
"total": 396.1774842810597,
"count": 233624,
"self": 15.486359806064229,
"children": {
"TorchPolicy.evaluate": {
"total": 380.6911244749955,
"count": 222966,
"self": 380.6911244749955
}
}
},
"workers": {
"total": 2.583710477070099,
"count": 233624,
"self": 0.0,
"children": {
"worker_root": {
"total": 2402.877974203026,
"count": 233624,
"is_parallel": true,
"self": 1194.0955956880057,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009025169999858917,
"count": 1,
"is_parallel": true,
"self": 0.00026339099997585436,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006391260000100374,
"count": 2,
"is_parallel": true,
"self": 0.0006391260000100374
}
}
},
"UnityEnvironment.step": {
"total": 0.07306453199998941,
"count": 1,
"is_parallel": true,
"self": 0.0003273449999596778,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018825200004357612,
"count": 1,
"is_parallel": true,
"self": 0.00018825200004357612
},
"communicator.exchange": {
"total": 0.07183092699995086,
"count": 1,
"is_parallel": true,
"self": 0.07183092699995086
},
"steps_from_proto": {
"total": 0.0007180080000352973,
"count": 1,
"is_parallel": true,
"self": 0.000202012999920953,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005159950001143443,
"count": 2,
"is_parallel": true,
"self": 0.0005159950001143443
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1208.7823785150204,
"count": 233623,
"is_parallel": true,
"self": 36.57585565781983,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.23595456314968,
"count": 233623,
"is_parallel": true,
"self": 78.23595456314968
},
"communicator.exchange": {
"total": 1008.60583474411,
"count": 233623,
"is_parallel": true,
"self": 1008.60583474411
},
"steps_from_proto": {
"total": 85.36473354994087,
"count": 233623,
"is_parallel": true,
"self": 29.952705176076847,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.41202837386402,
"count": 467246,
"is_parallel": true,
"self": 55.41202837386402
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 516.3098528020631,
"count": 233624,
"self": 6.532905711121771,
"children": {
"process_trajectory": {
"total": 168.43580487094027,
"count": 233624,
"self": 167.2845951409406,
"children": {
"RLTrainer._checkpoint": {
"total": 1.151209729999664,
"count": 10,
"self": 1.151209729999664
}
}
},
"_update_policy": {
"total": 341.3411422200011,
"count": 97,
"self": 255.0505774690124,
"children": {
"TorchPPOOptimizer.update": {
"total": 86.29056475098866,
"count": 5820,
"self": 86.29056475098866
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.37000095291296e-07,
"count": 1,
"self": 9.37000095291296e-07
},
"TrainerController._save_models": {
"total": 0.10348829499980639,
"count": 1,
"self": 0.0016100399998322246,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10187825499997416,
"count": 1,
"self": 0.10187825499997416
}
}
}
}
}
}
}