ppo-Huggy / run_logs /timers.json
mjishu's picture
Huggy
a820836 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4050296545028687,
"min": 1.4050296545028687,
"max": 1.4284862279891968,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71112.765625,
"min": 67693.5,
"max": 76695.140625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 80.96885245901639,
"min": 77.89291338582677,
"max": 418.3,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49391.0,
"min": 48806.0,
"max": 50196.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999921.0,
"min": 49871.0,
"max": 1999921.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999921.0,
"min": 49871.0,
"max": 1999921.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4433658123016357,
"min": 0.1485568881034851,
"max": 2.4907994270324707,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1490.453125,
"min": 17.67827033996582,
"max": 1545.8597412109375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.834140026862504,
"min": 1.7926167304776295,
"max": 4.00570282002665,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2338.8254163861275,
"min": 213.32139092683792,
"max": 2466.134217619896,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.834140026862504,
"min": 1.7926167304776295,
"max": 4.00570282002665,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2338.8254163861275,
"min": 213.32139092683792,
"max": 2466.134217619896,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016801994805508813,
"min": 0.013758243092646201,
"max": 0.021082016747095624,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05040598441652644,
"min": 0.027516486185292403,
"max": 0.05548951492916482,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05888152246673902,
"min": 0.022332535497844218,
"max": 0.06392764213184515,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17664456740021706,
"min": 0.044665070995688436,
"max": 0.19178292639553546,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3989488670499873e-06,
"min": 3.3989488670499873e-06,
"max": 0.000295303876565375,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0196846601149962e-05,
"min": 1.0196846601149962e-05,
"max": 0.0008437395187534997,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10113294999999999,
"min": 0.10113294999999999,
"max": 0.19843462500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30339884999999994,
"min": 0.20739955,
"max": 0.5812465,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.653420499999977e-05,
"min": 6.653420499999977e-05,
"max": 0.0049218877875,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001996026149999993,
"min": 0.0001996026149999993,
"max": 0.01406420035,
"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": "1739058841",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1739061323"
},
"total": 2482.205041695,
"count": 1,
"self": 0.4360873580003499,
"children": {
"run_training.setup": {
"total": 0.024720613999988927,
"count": 1,
"self": 0.024720613999988927
},
"TrainerController.start_learning": {
"total": 2481.744233723,
"count": 1,
"self": 4.5214566069430475,
"children": {
"TrainerController._reset_env": {
"total": 3.2632415310000624,
"count": 1,
"self": 3.2632415310000624
},
"TrainerController.advance": {
"total": 2473.848107310057,
"count": 232678,
"self": 4.751430588047242,
"children": {
"env_step": {
"total": 1962.733042740911,
"count": 232678,
"self": 1532.444937788821,
"children": {
"SubprocessEnvManager._take_step": {
"total": 427.5851453790701,
"count": 232678,
"self": 15.962345510097407,
"children": {
"TorchPolicy.evaluate": {
"total": 411.6227998689727,
"count": 222966,
"self": 411.6227998689727
}
}
},
"workers": {
"total": 2.7029595730198253,
"count": 232678,
"self": 0.0,
"children": {
"worker_root": {
"total": 2474.2869838660067,
"count": 232678,
"is_parallel": true,
"self": 1226.383357407995,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010522119999905044,
"count": 1,
"is_parallel": true,
"self": 0.0003720400000020163,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006801719999884881,
"count": 2,
"is_parallel": true,
"self": 0.0006801719999884881
}
}
},
"UnityEnvironment.step": {
"total": 0.032425170999999864,
"count": 1,
"is_parallel": true,
"self": 0.000311150000015914,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000244412000029115,
"count": 1,
"is_parallel": true,
"self": 0.000244412000029115
},
"communicator.exchange": {
"total": 0.031177015000025676,
"count": 1,
"is_parallel": true,
"self": 0.031177015000025676
},
"steps_from_proto": {
"total": 0.0006925939999291586,
"count": 1,
"is_parallel": true,
"self": 0.00020390499980749155,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000488689000121667,
"count": 2,
"is_parallel": true,
"self": 0.000488689000121667
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1247.9036264580118,
"count": 232677,
"is_parallel": true,
"self": 38.01481937415292,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.26936198500232,
"count": 232677,
"is_parallel": true,
"self": 82.26936198500232
},
"communicator.exchange": {
"total": 1039.8546182678906,
"count": 232677,
"is_parallel": true,
"self": 1039.8546182678906
},
"steps_from_proto": {
"total": 87.76482683096583,
"count": 232677,
"is_parallel": true,
"self": 30.925630224928682,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.83919660603715,
"count": 465354,
"is_parallel": true,
"self": 56.83919660603715
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 506.3636339810986,
"count": 232678,
"self": 6.70267859213493,
"children": {
"process_trajectory": {
"total": 165.18472832496423,
"count": 232678,
"self": 163.76831796796387,
"children": {
"RLTrainer._checkpoint": {
"total": 1.416410357000359,
"count": 10,
"self": 1.416410357000359
}
}
},
"_update_policy": {
"total": 334.47622706399943,
"count": 97,
"self": 267.22324654100805,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.25298052299138,
"count": 2910,
"self": 67.25298052299138
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.649997991800774e-07,
"count": 1,
"self": 9.649997991800774e-07
},
"TrainerController._save_models": {
"total": 0.11142731000018102,
"count": 1,
"self": 0.0018329830004404357,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10959432699974059,
"count": 1,
"self": 0.10959432699974059
}
}
}
}
}
}
}