ppo-Huggy / run_logs /timers.json
twosocksinoneshoe's picture
Huggy
8b649e9 verified
raw
history blame
No virus
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.407840609550476,
"min": 1.407840609550476,
"max": 1.429144263267517,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71749.1875,
"min": 68931.5625,
"max": 78066.7421875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 103.0843621399177,
"min": 87.7513321492007,
"max": 384.94615384615383,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50099.0,
"min": 48945.0,
"max": 50182.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999921.0,
"min": 49647.0,
"max": 1999921.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999921.0,
"min": 49647.0,
"max": 1999921.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3825888633728027,
"min": 0.005514174699783325,
"max": 2.439969539642334,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1157.938232421875,
"min": 0.7113285064697266,
"max": 1334.83642578125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.739463228870321,
"min": 1.754799653970918,
"max": 3.8536894930792704,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1817.379129230976,
"min": 226.36915536224842,
"max": 2137.833092570305,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.739463228870321,
"min": 1.754799653970918,
"max": 3.8536894930792704,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1817.379129230976,
"min": 226.36915536224842,
"max": 2137.833092570305,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016728494506646208,
"min": 0.01388535990845412,
"max": 0.02195849346947701,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05018548351993862,
"min": 0.02777071981690824,
"max": 0.06123423686561485,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04927000030875206,
"min": 0.02305269952242573,
"max": 0.05565638480087121,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14781000092625618,
"min": 0.04610539904485146,
"max": 0.16326373058060806,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.217948927383334e-06,
"min": 3.217948927383334e-06,
"max": 0.0002953568265477249,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.653846782150001e-06,
"min": 9.653846782150001e-06,
"max": 0.00084381196872935,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10107261666666666,
"min": 0.10107261666666666,
"max": 0.19845227499999996,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30321784999999996,
"min": 0.20727470000000003,
"max": 0.58127065,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.352357166666666e-05,
"min": 6.352357166666666e-05,
"max": 0.004922768522500002,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019057071499999998,
"min": 0.00019057071499999998,
"max": 0.014065405435000001,
"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": "1716991993",
"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": "1716994389"
},
"total": 2396.827412924,
"count": 1,
"self": 0.44061741099994833,
"children": {
"run_training.setup": {
"total": 0.054998038999997334,
"count": 1,
"self": 0.054998038999997334
},
"TrainerController.start_learning": {
"total": 2396.331797474,
"count": 1,
"self": 4.26511110003139,
"children": {
"TrainerController._reset_env": {
"total": 3.0528788260000397,
"count": 1,
"self": 3.0528788260000397
},
"TrainerController.advance": {
"total": 2388.8719458539686,
"count": 231605,
"self": 4.602883068987921,
"children": {
"env_step": {
"total": 1896.9297721680407,
"count": 231605,
"self": 1568.4137467991147,
"children": {
"SubprocessEnvManager._take_step": {
"total": 325.6937305749592,
"count": 231605,
"self": 17.30963048402333,
"children": {
"TorchPolicy.evaluate": {
"total": 308.3841000909359,
"count": 223064,
"self": 308.3841000909359
}
}
},
"workers": {
"total": 2.822294793966819,
"count": 231605,
"self": 0.0,
"children": {
"worker_root": {
"total": 2389.056150725018,
"count": 231605,
"is_parallel": true,
"self": 1126.5824926940938,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008296480000353768,
"count": 1,
"is_parallel": true,
"self": 0.00021063900004492098,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006190089999904558,
"count": 2,
"is_parallel": true,
"self": 0.0006190089999904558
}
}
},
"UnityEnvironment.step": {
"total": 0.0362182369999573,
"count": 1,
"is_parallel": true,
"self": 0.00040040799996177157,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023803100003760846,
"count": 1,
"is_parallel": true,
"self": 0.00023803100003760846
},
"communicator.exchange": {
"total": 0.03482004099998903,
"count": 1,
"is_parallel": true,
"self": 0.03482004099998903
},
"steps_from_proto": {
"total": 0.0007597569999688858,
"count": 1,
"is_parallel": true,
"self": 0.00019443499996896207,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005653219999999237,
"count": 2,
"is_parallel": true,
"self": 0.0005653219999999237
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1262.4736580309243,
"count": 231604,
"is_parallel": true,
"self": 38.62469107374068,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.5417410190339,
"count": 231604,
"is_parallel": true,
"self": 80.5417410190339
},
"communicator.exchange": {
"total": 1054.5980157820766,
"count": 231604,
"is_parallel": true,
"self": 1054.5980157820766
},
"steps_from_proto": {
"total": 88.7092101560732,
"count": 231604,
"is_parallel": true,
"self": 31.413053846023104,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.296156310050094,
"count": 463208,
"is_parallel": true,
"self": 57.296156310050094
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 487.33929061694005,
"count": 231605,
"self": 6.677936155967359,
"children": {
"process_trajectory": {
"total": 149.00216911897377,
"count": 231605,
"self": 147.65032409497354,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3518450240002267,
"count": 10,
"self": 1.3518450240002267
}
}
},
"_update_policy": {
"total": 331.6591853419989,
"count": 97,
"self": 267.9974114160024,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.6617739259965,
"count": 2910,
"self": 63.6617739259965
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5430000530614052e-06,
"count": 1,
"self": 1.5430000530614052e-06
},
"TrainerController._save_models": {
"total": 0.1418601509999462,
"count": 1,
"self": 0.0022239099998841994,
"children": {
"RLTrainer._checkpoint": {
"total": 0.139636241000062,
"count": 1,
"self": 0.139636241000062
}
}
}
}
}
}
}