ppo-Huggy / run_logs /timers.json
BMukhtar's picture
Huggy
84cd125 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.403105616569519,
"min": 1.403105616569519,
"max": 1.4262750148773193,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70729.1484375,
"min": 68936.6171875,
"max": 78489.1640625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 83.45101351351352,
"min": 77.20813771517997,
"max": 371.46666666666664,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49403.0,
"min": 48793.0,
"max": 50148.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999946.0,
"min": 49968.0,
"max": 1999946.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999946.0,
"min": 49968.0,
"max": 1999946.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.429173231124878,
"min": 0.11701562255620956,
"max": 2.489457130432129,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1438.070556640625,
"min": 15.680093765258789,
"max": 1540.8369140625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6564898090185345,
"min": 1.880803546798763,
"max": 3.9927546657971886,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2164.6419669389725,
"min": 252.02767527103424,
"max": 2471.884281218052,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6564898090185345,
"min": 1.880803546798763,
"max": 3.9927546657971886,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2164.6419669389725,
"min": 252.02767527103424,
"max": 2471.884281218052,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015824631816253206,
"min": 0.01333957627874851,
"max": 0.02007337749625246,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04747389544875962,
"min": 0.028178922786416177,
"max": 0.05883610782038886,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05859845988452434,
"min": 0.021915697616835435,
"max": 0.0645579212034742,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17579537965357303,
"min": 0.04383139523367087,
"max": 0.17579537965357303,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.796298734600004e-06,
"min": 3.796298734600004e-06,
"max": 0.00029531655156114995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1388896203800013e-05,
"min": 1.1388896203800013e-05,
"max": 0.0008440002186665999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1012654,
"min": 0.1012654,
"max": 0.19843885000000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3037962,
"min": 0.20769804999999997,
"max": 0.5813334,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.314346000000009e-05,
"min": 7.314346000000009e-05,
"max": 0.0049220986149999995,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021943038000000025,
"min": 0.00021943038000000025,
"max": 0.014068536660000006,
"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": "1720087859",
"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": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1720090357"
},
"total": 2498.139039205,
"count": 1,
"self": 0.43799647799914965,
"children": {
"run_training.setup": {
"total": 0.05585843699986981,
"count": 1,
"self": 0.05585843699986981
},
"TrainerController.start_learning": {
"total": 2497.6451842900005,
"count": 1,
"self": 4.421928591002143,
"children": {
"TrainerController._reset_env": {
"total": 3.0107570729999225,
"count": 1,
"self": 3.0107570729999225
},
"TrainerController.advance": {
"total": 2490.095620782998,
"count": 233267,
"self": 5.081911717100866,
"children": {
"env_step": {
"total": 1981.8358876008078,
"count": 233267,
"self": 1636.9329000918583,
"children": {
"SubprocessEnvManager._take_step": {
"total": 341.85116860898916,
"count": 233267,
"self": 16.799991924031247,
"children": {
"TorchPolicy.evaluate": {
"total": 325.0511766849579,
"count": 223025,
"self": 325.0511766849579
}
}
},
"workers": {
"total": 3.051818899960381,
"count": 233267,
"self": 0.0,
"children": {
"worker_root": {
"total": 2490.328901332061,
"count": 233267,
"is_parallel": true,
"self": 1173.5427407420839,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000928418000057718,
"count": 1,
"is_parallel": true,
"self": 0.0002691880001748359,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006592299998828821,
"count": 2,
"is_parallel": true,
"self": 0.0006592299998828821
}
}
},
"UnityEnvironment.step": {
"total": 0.03587621099995886,
"count": 1,
"is_parallel": true,
"self": 0.0004530559997419914,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022214600016923214,
"count": 1,
"is_parallel": true,
"self": 0.00022214600016923214
},
"communicator.exchange": {
"total": 0.03437678099999175,
"count": 1,
"is_parallel": true,
"self": 0.03437678099999175
},
"steps_from_proto": {
"total": 0.0008242280000558821,
"count": 1,
"is_parallel": true,
"self": 0.00024364600017179328,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005805819998840889,
"count": 2,
"is_parallel": true,
"self": 0.0005805819998840889
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1316.786160589977,
"count": 233266,
"is_parallel": true,
"self": 40.462097355981086,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.19346343194184,
"count": 233266,
"is_parallel": true,
"self": 86.19346343194184
},
"communicator.exchange": {
"total": 1097.305017226971,
"count": 233266,
"is_parallel": true,
"self": 1097.305017226971
},
"steps_from_proto": {
"total": 92.82558257508322,
"count": 233266,
"is_parallel": true,
"self": 34.98103163238261,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.84455094270061,
"count": 466532,
"is_parallel": true,
"self": 57.84455094270061
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 503.17782146508944,
"count": 233267,
"self": 7.069252415186384,
"children": {
"process_trajectory": {
"total": 162.2847507139038,
"count": 233267,
"self": 160.84187632290445,
"children": {
"RLTrainer._checkpoint": {
"total": 1.44287439099935,
"count": 10,
"self": 1.44287439099935
}
}
},
"_update_policy": {
"total": 333.82381833599925,
"count": 97,
"self": 270.1351233650025,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.68869497099672,
"count": 2910,
"self": 63.68869497099672
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0650001058820635e-06,
"count": 1,
"self": 1.0650001058820635e-06
},
"TrainerController._save_models": {
"total": 0.11687677800000529,
"count": 1,
"self": 0.004315075000249635,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11256170299975565,
"count": 1,
"self": 0.11256170299975565
}
}
}
}
}
}
}