ppo-Huggy / run_logs /timers.json
c-g's picture
Huggy
be43aea
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4096297025680542,
"min": 1.4096297025680542,
"max": 1.4291694164276123,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69360.828125,
"min": 68888.6484375,
"max": 78622.609375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 104.09243697478992,
"min": 92.99624060150376,
"max": 362.036231884058,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49548.0,
"min": 48923.0,
"max": 50093.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999973.0,
"min": 49953.0,
"max": 1999973.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999973.0,
"min": 49953.0,
"max": 1999973.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.39812970161438,
"min": 0.06847546994686127,
"max": 2.4438111782073975,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1141.509765625,
"min": 9.381139755249023,
"max": 1254.365478515625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6606302010912857,
"min": 1.7982644279942894,
"max": 3.8825077395324015,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1742.459975719452,
"min": 246.36222663521767,
"max": 1979.4625475406647,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6606302010912857,
"min": 1.7982644279942894,
"max": 3.8825077395324015,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1742.459975719452,
"min": 246.36222663521767,
"max": 1979.4625475406647,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01634341262106318,
"min": 0.013859557439476096,
"max": 0.019538614121847785,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03268682524212636,
"min": 0.027719114878952192,
"max": 0.05612832515810927,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04577920039494832,
"min": 0.022529107456405958,
"max": 0.05572443612747722,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09155840078989665,
"min": 0.045058214912811916,
"max": 0.16717330838243166,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.663523445524999e-06,
"min": 4.663523445524999e-06,
"max": 0.00029537130154289997,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.327046891049998e-06,
"min": 9.327046891049998e-06,
"max": 0.0008442360185880001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10155447499999998,
"min": 0.10155447499999998,
"max": 0.19845710000000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20310894999999995,
"min": 0.20310894999999995,
"max": 0.5814119999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.756830249999998e-05,
"min": 8.756830249999998e-05,
"max": 0.0049230092900000005,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017513660499999997,
"min": 0.00017513660499999997,
"max": 0.014072458800000003,
"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": "1694852034",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1694854715"
},
"total": 2680.425059942,
"count": 1,
"self": 0.4906029110002237,
"children": {
"run_training.setup": {
"total": 0.04562810300012643,
"count": 1,
"self": 0.04562810300012643
},
"TrainerController.start_learning": {
"total": 2679.888828928,
"count": 1,
"self": 5.232525054904272,
"children": {
"TrainerController._reset_env": {
"total": 4.278837801000009,
"count": 1,
"self": 4.278837801000009
},
"TrainerController.advance": {
"total": 2670.249503649096,
"count": 231477,
"self": 5.637800105032966,
"children": {
"env_step": {
"total": 2094.1186377680674,
"count": 231477,
"self": 1763.7937314560193,
"children": {
"SubprocessEnvManager._take_step": {
"total": 326.942406113154,
"count": 231477,
"self": 19.124037656278006,
"children": {
"TorchPolicy.evaluate": {
"total": 307.818368456876,
"count": 222946,
"self": 307.818368456876
}
}
},
"workers": {
"total": 3.3825001988941494,
"count": 231477,
"self": 0.0,
"children": {
"worker_root": {
"total": 2671.3918851682083,
"count": 231477,
"is_parallel": true,
"self": 1236.482233814335,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010330379998322314,
"count": 1,
"is_parallel": true,
"self": 0.0002523469997868233,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007806910000454081,
"count": 2,
"is_parallel": true,
"self": 0.0007806910000454081
}
}
},
"UnityEnvironment.step": {
"total": 0.03209197299997868,
"count": 1,
"is_parallel": true,
"self": 0.00039950300015334506,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002206760000262875,
"count": 1,
"is_parallel": true,
"self": 0.0002206760000262875
},
"communicator.exchange": {
"total": 0.030610450999802197,
"count": 1,
"is_parallel": true,
"self": 0.030610450999802197
},
"steps_from_proto": {
"total": 0.0008613429999968503,
"count": 1,
"is_parallel": true,
"self": 0.0002508390000457439,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006105039999511064,
"count": 2,
"is_parallel": true,
"self": 0.0006105039999511064
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1434.9096513538734,
"count": 231476,
"is_parallel": true,
"self": 42.82791112173277,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 88.96219564005582,
"count": 231476,
"is_parallel": true,
"self": 88.96219564005582
},
"communicator.exchange": {
"total": 1194.8234692430644,
"count": 231476,
"is_parallel": true,
"self": 1194.8234692430644
},
"steps_from_proto": {
"total": 108.29607534902038,
"count": 231476,
"is_parallel": true,
"self": 40.28281728592697,
"children": {
"_process_rank_one_or_two_observation": {
"total": 68.01325806309342,
"count": 462952,
"is_parallel": true,
"self": 68.01325806309342
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 570.4930657759958,
"count": 231477,
"self": 7.795360963000348,
"children": {
"process_trajectory": {
"total": 147.4942294139953,
"count": 231477,
"self": 145.9410508969945,
"children": {
"RLTrainer._checkpoint": {
"total": 1.553178517000788,
"count": 10,
"self": 1.553178517000788
}
}
},
"_update_policy": {
"total": 415.2034753990001,
"count": 96,
"self": 353.9939687859976,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.20950661300253,
"count": 2880,
"self": 61.20950661300253
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.619998309062794e-07,
"count": 1,
"self": 9.619998309062794e-07
},
"TrainerController._save_models": {
"total": 0.12796146099981343,
"count": 1,
"self": 0.0021109760000399547,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12585048499977347,
"count": 1,
"self": 0.12585048499977347
}
}
}
}
}
}
}