ppo-Huggy / run_logs /timers.json
oerdal's picture
Huggy
637bcdd verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4111793041229248,
"min": 1.4111793041229248,
"max": 1.4326120615005493,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70190.6484375,
"min": 68578.96875,
"max": 77505.6171875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 108.76805251641137,
"min": 96.02718446601942,
"max": 418.1333333333333,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49707.0,
"min": 49231.0,
"max": 50176.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999675.0,
"min": 49709.0,
"max": 1999675.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999675.0,
"min": 49709.0,
"max": 1999675.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.332772731781006,
"min": 0.25474587082862854,
"max": 2.393850088119507,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1066.0771484375,
"min": 30.314760208129883,
"max": 1187.184814453125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.619091333654308,
"min": 1.8791949533614791,
"max": 3.877808934333278,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1653.9247394800186,
"min": 223.62419945001602,
"max": 1848.4088249206543,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.619091333654308,
"min": 1.8791949533614791,
"max": 3.877808934333278,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1653.9247394800186,
"min": 223.62419945001602,
"max": 1848.4088249206543,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014269884822230475,
"min": 0.013026065821759403,
"max": 0.02011864527755986,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.02853976964446095,
"min": 0.026052131643518807,
"max": 0.060355935832679584,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.049900829295317334,
"min": 0.019274035561829807,
"max": 0.06218675660590331,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09980165859063467,
"min": 0.038548071123659614,
"max": 0.18023924008011816,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.3632985456e-06,
"min": 4.3632985456e-06,
"max": 0.00029529037656987503,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.7265970912e-06,
"min": 8.7265970912e-06,
"max": 0.0008439603186798999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1014544,
"min": 0.1014544,
"max": 0.19843012500000007,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.2029088,
"min": 0.2029088,
"max": 0.5813201,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.257456e-05,
"min": 8.257456e-05,
"max": 0.0049216632375,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016514912,
"min": 0.00016514912,
"max": 0.014067872990000002,
"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": "1710444206",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1710446607"
},
"total": 2401.3181099760004,
"count": 1,
"self": 0.7385221260001344,
"children": {
"run_training.setup": {
"total": 0.060334681000085766,
"count": 1,
"self": 0.060334681000085766
},
"TrainerController.start_learning": {
"total": 2400.519253169,
"count": 1,
"self": 4.268642058972546,
"children": {
"TrainerController._reset_env": {
"total": 3.2671930039998642,
"count": 1,
"self": 3.2671930039998642
},
"TrainerController.advance": {
"total": 2392.7999346560273,
"count": 231013,
"self": 4.553417858191551,
"children": {
"env_step": {
"total": 1922.8656954019389,
"count": 231013,
"self": 1594.8062976809872,
"children": {
"SubprocessEnvManager._take_step": {
"total": 325.21905063894314,
"count": 231013,
"self": 17.45241470883252,
"children": {
"TorchPolicy.evaluate": {
"total": 307.7666359301106,
"count": 222901,
"self": 307.7666359301106
}
}
},
"workers": {
"total": 2.8403470820085204,
"count": 231013,
"self": 0.0,
"children": {
"worker_root": {
"total": 2393.290388291982,
"count": 231013,
"is_parallel": true,
"self": 1101.1547649537754,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009037370000442024,
"count": 1,
"is_parallel": true,
"self": 0.00025140900015685475,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006523279998873477,
"count": 2,
"is_parallel": true,
"self": 0.0006523279998873477
}
}
},
"UnityEnvironment.step": {
"total": 0.03217147300006218,
"count": 1,
"is_parallel": true,
"self": 0.0003967879999891011,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021357200012062094,
"count": 1,
"is_parallel": true,
"self": 0.00021357200012062094
},
"communicator.exchange": {
"total": 0.030735090000007403,
"count": 1,
"is_parallel": true,
"self": 0.030735090000007403
},
"steps_from_proto": {
"total": 0.000826022999945053,
"count": 1,
"is_parallel": true,
"self": 0.00021165899988773162,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006143640000573214,
"count": 2,
"is_parallel": true,
"self": 0.0006143640000573214
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1292.1356233382064,
"count": 231012,
"is_parallel": true,
"self": 39.33297555939316,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.47029796109109,
"count": 231012,
"is_parallel": true,
"self": 82.47029796109109
},
"communicator.exchange": {
"total": 1078.527366595907,
"count": 231012,
"is_parallel": true,
"self": 1078.527366595907
},
"steps_from_proto": {
"total": 91.80498322181506,
"count": 231012,
"is_parallel": true,
"self": 32.73256021578436,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.072423006030704,
"count": 462024,
"is_parallel": true,
"self": 59.072423006030704
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 465.3808213958969,
"count": 231013,
"self": 7.069562241816357,
"children": {
"process_trajectory": {
"total": 145.96968846108007,
"count": 231013,
"self": 144.54232706708035,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4273613939997176,
"count": 10,
"self": 1.4273613939997176
}
}
},
"_update_policy": {
"total": 312.34157069300045,
"count": 96,
"self": 249.81802923900386,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.523541453996586,
"count": 2880,
"self": 62.523541453996586
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0980002116411924e-06,
"count": 1,
"self": 1.0980002116411924e-06
},
"TrainerController._save_models": {
"total": 0.18348235200028284,
"count": 1,
"self": 0.0030942630005483807,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18038808899973446,
"count": 1,
"self": 0.18038808899973446
}
}
}
}
}
}
}