ppo-Huggy / run_logs /timers.json
williamcorrias's picture
Huggy
c706499 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4024159908294678,
"min": 1.4024159908294678,
"max": 1.4253385066986084,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68566.921875,
"min": 68566.921875,
"max": 76066.6171875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 88.79136690647482,
"min": 86.06666666666666,
"max": 391.0703125,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49368.0,
"min": 49058.0,
"max": 50057.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999978.0,
"min": 49920.0,
"max": 1999978.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999978.0,
"min": 49920.0,
"max": 1999978.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4751932621002197,
"min": 0.137735977768898,
"max": 2.4901108741760254,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1376.2073974609375,
"min": 17.492469787597656,
"max": 1392.476806640625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8487918329753463,
"min": 1.748872861852796,
"max": 3.8487918329753463,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2139.9282591342926,
"min": 222.1068534553051,
"max": 2163.7646141648293,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8487918329753463,
"min": 1.748872861852796,
"max": 3.8487918329753463,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2139.9282591342926,
"min": 222.1068534553051,
"max": 2163.7646141648293,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01647733761282224,
"min": 0.013273295913192366,
"max": 0.020047350829635335,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04943201283846672,
"min": 0.026546591826384733,
"max": 0.060142052488906,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05568208599256145,
"min": 0.02045952345555027,
"max": 0.06047427666683991,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16704625797768435,
"min": 0.04091904691110054,
"max": 0.17483661783238252,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.2752489082833274e-06,
"min": 3.2752489082833274e-06,
"max": 0.0002953696515434499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.825746724849982e-06,
"min": 9.825746724849982e-06,
"max": 0.0008443254185581996,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10109171666666668,
"min": 0.10109171666666668,
"max": 0.19845655,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30327515000000005,
"min": 0.20733104999999993,
"max": 0.5814418000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.447666166666656e-05,
"min": 6.447666166666656e-05,
"max": 0.004922981845000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019342998499999968,
"min": 0.00019342998499999968,
"max": 0.01407394582,
"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": "1735840337",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1735842828"
},
"total": 2491.348130325,
"count": 1,
"self": 0.6458128570002373,
"children": {
"run_training.setup": {
"total": 0.05773652299990317,
"count": 1,
"self": 0.05773652299990317
},
"TrainerController.start_learning": {
"total": 2490.6445809449997,
"count": 1,
"self": 4.631643498880749,
"children": {
"TrainerController._reset_env": {
"total": 5.904291626000031,
"count": 1,
"self": 5.904291626000031
},
"TrainerController.advance": {
"total": 2479.938724881119,
"count": 232154,
"self": 4.663711557089755,
"children": {
"env_step": {
"total": 1963.8265038710217,
"count": 232154,
"self": 1545.1275393879598,
"children": {
"SubprocessEnvManager._take_step": {
"total": 415.882329890027,
"count": 232154,
"self": 16.04214506095275,
"children": {
"TorchPolicy.evaluate": {
"total": 399.84018482907425,
"count": 222846,
"self": 399.84018482907425
}
}
},
"workers": {
"total": 2.8166345930349053,
"count": 232154,
"self": 0.0,
"children": {
"worker_root": {
"total": 2483.1969379789384,
"count": 232154,
"is_parallel": true,
"self": 1226.0076594460122,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008726880000722304,
"count": 1,
"is_parallel": true,
"self": 0.00026150200017127645,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006111859999009539,
"count": 2,
"is_parallel": true,
"self": 0.0006111859999009539
}
}
},
"UnityEnvironment.step": {
"total": 0.03013016800002788,
"count": 1,
"is_parallel": true,
"self": 0.00037040699999124627,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000206303999902957,
"count": 1,
"is_parallel": true,
"self": 0.000206303999902957
},
"communicator.exchange": {
"total": 0.028772867000043334,
"count": 1,
"is_parallel": true,
"self": 0.028772867000043334
},
"steps_from_proto": {
"total": 0.0007805900000903421,
"count": 1,
"is_parallel": true,
"self": 0.00021141800016266643,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005691719999276756,
"count": 2,
"is_parallel": true,
"self": 0.0005691719999276756
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1257.1892785329262,
"count": 232153,
"is_parallel": true,
"self": 37.975523168822974,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.43386008516723,
"count": 232153,
"is_parallel": true,
"self": 83.43386008516723
},
"communicator.exchange": {
"total": 1045.062388371914,
"count": 232153,
"is_parallel": true,
"self": 1045.062388371914
},
"steps_from_proto": {
"total": 90.71750690702208,
"count": 232153,
"is_parallel": true,
"self": 34.11518037993892,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.602326527083164,
"count": 464306,
"is_parallel": true,
"self": 56.602326527083164
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 511.44850945300766,
"count": 232154,
"self": 6.6986442299891,
"children": {
"process_trajectory": {
"total": 169.42637574401726,
"count": 232154,
"self": 168.09179575401788,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3345799899993835,
"count": 10,
"self": 1.3345799899993835
}
}
},
"_update_policy": {
"total": 335.3234894790013,
"count": 97,
"self": 269.3194889010043,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.00400057799698,
"count": 2910,
"self": 66.00400057799698
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4859997463645414e-06,
"count": 1,
"self": 1.4859997463645414e-06
},
"TrainerController._save_models": {
"total": 0.16991945300014777,
"count": 1,
"self": 0.003044183000383782,
"children": {
"RLTrainer._checkpoint": {
"total": 0.166875269999764,
"count": 1,
"self": 0.166875269999764
}
}
}
}
}
}
}