ppo-Huggy / run_logs /timers.json
pb96's picture
Unit-1 Huggy
6e19f84 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4116381406784058,
"min": 1.4116381406784058,
"max": 1.43100106716156,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69864.796875,
"min": 68591.078125,
"max": 78956.203125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 81.81574539363484,
"min": 78.50885668276973,
"max": 397.8253968253968,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 48844.0,
"min": 48754.0,
"max": 50126.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999991.0,
"min": 49992.0,
"max": 1999991.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999991.0,
"min": 49992.0,
"max": 1999991.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.490117073059082,
"min": 0.06845264136791229,
"max": 2.512019395828247,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1486.599853515625,
"min": 8.556580543518066,
"max": 1542.3798828125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.832284152607622,
"min": 1.906990761756897,
"max": 3.9729365702347246,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2287.8736391067505,
"min": 238.37384521961212,
"max": 2421.3406006097794,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.832284152607622,
"min": 1.906990761756897,
"max": 3.9729365702347246,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2287.8736391067505,
"min": 238.37384521961212,
"max": 2421.3406006097794,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015054109161428643,
"min": 0.01353283562893921,
"max": 0.020633406421661168,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.045162327484285926,
"min": 0.02706567125787842,
"max": 0.06190021926498351,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05244791300760374,
"min": 0.021516693104058505,
"max": 0.06032930954049032,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15734373902281124,
"min": 0.04303338620811701,
"max": 0.17378094059725602,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5874488042166555e-06,
"min": 3.5874488042166555e-06,
"max": 0.0002952796515734499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0762346412649967e-05,
"min": 1.0762346412649967e-05,
"max": 0.0008440020186659998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10119578333333333,
"min": 0.10119578333333333,
"max": 0.19842655000000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30358735,
"min": 0.20753025000000003,
"max": 0.581334,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.966958833333317e-05,
"min": 6.966958833333317e-05,
"max": 0.004921484845000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020900876499999952,
"min": 0.00020900876499999952,
"max": 0.014068566600000002,
"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": "1751584631",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1751587136"
},
"total": 2505.741584782,
"count": 1,
"self": 0.4385876249998546,
"children": {
"run_training.setup": {
"total": 0.023003938999977436,
"count": 1,
"self": 0.023003938999977436
},
"TrainerController.start_learning": {
"total": 2505.279993218,
"count": 1,
"self": 5.045278155012056,
"children": {
"TrainerController._reset_env": {
"total": 3.285350047999998,
"count": 1,
"self": 3.285350047999998
},
"TrainerController.advance": {
"total": 2496.843659768988,
"count": 232675,
"self": 4.761450715850515,
"children": {
"env_step": {
"total": 2018.28042807906,
"count": 232675,
"self": 1594.4553175170602,
"children": {
"SubprocessEnvManager._take_step": {
"total": 420.9534521089767,
"count": 232675,
"self": 16.321436647969506,
"children": {
"TorchPolicy.evaluate": {
"total": 404.6320154610072,
"count": 222992,
"self": 404.6320154610072
}
}
},
"workers": {
"total": 2.8716584530230875,
"count": 232675,
"self": 0.0,
"children": {
"worker_root": {
"total": 2497.103998692058,
"count": 232675,
"is_parallel": true,
"self": 1198.0794424990954,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008678539999777968,
"count": 1,
"is_parallel": true,
"self": 0.0002386060000389989,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006292479999387979,
"count": 2,
"is_parallel": true,
"self": 0.0006292479999387979
}
}
},
"UnityEnvironment.step": {
"total": 0.0695084469999756,
"count": 1,
"is_parallel": true,
"self": 0.00035633399994594583,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019656300003134675,
"count": 1,
"is_parallel": true,
"self": 0.00019656300003134675
},
"communicator.exchange": {
"total": 0.06825447800002848,
"count": 1,
"is_parallel": true,
"self": 0.06825447800002848
},
"steps_from_proto": {
"total": 0.0007010719999698267,
"count": 1,
"is_parallel": true,
"self": 0.0001852289999533241,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005158430000165026,
"count": 2,
"is_parallel": true,
"self": 0.0005158430000165026
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1299.0245561929628,
"count": 232674,
"is_parallel": true,
"self": 37.977732701007426,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.12550033396644,
"count": 232674,
"is_parallel": true,
"self": 79.12550033396644
},
"communicator.exchange": {
"total": 1093.1780751709873,
"count": 232674,
"is_parallel": true,
"self": 1093.1780751709873
},
"steps_from_proto": {
"total": 88.74324798700167,
"count": 232674,
"is_parallel": true,
"self": 30.303310942089297,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.43993704491237,
"count": 465348,
"is_parallel": true,
"self": 58.43993704491237
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 473.8017809740776,
"count": 232675,
"self": 7.002356924115759,
"children": {
"process_trajectory": {
"total": 166.44001071795884,
"count": 232675,
"self": 165.28934970295876,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1506610150000824,
"count": 10,
"self": 1.1506610150000824
}
}
},
"_update_policy": {
"total": 300.359413332003,
"count": 97,
"self": 236.81685096800163,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.542562364001355,
"count": 2910,
"self": 63.542562364001355
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.099999260797631e-07,
"count": 1,
"self": 9.099999260797631e-07
},
"TrainerController._save_models": {
"total": 0.1057043360001444,
"count": 1,
"self": 0.001530347000425536,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10417398899971886,
"count": 1,
"self": 0.10417398899971886
}
}
}
}
}
}
}