ppo-Huggy / run_logs /timers.json
TomTom42's picture
Huggy
1fefd23 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4112904071807861,
"min": 1.4112904071807861,
"max": 1.4299709796905518,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71762.703125,
"min": 69301.5625,
"max": 76601.40625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 77.40188383045526,
"min": 71.68168604651163,
"max": 393.9133858267717,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49305.0,
"min": 49182.0,
"max": 50027.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999934.0,
"min": 49935.0,
"max": 1999934.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999934.0,
"min": 49935.0,
"max": 1999934.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.483818769454956,
"min": 0.10380341857671738,
"max": 2.530905246734619,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1582.1925048828125,
"min": 13.079230308532715,
"max": 1687.6722412109375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.824786412191915,
"min": 1.903725757958397,
"max": 3.9938355420796285,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2436.38894456625,
"min": 239.86944550275803,
"max": 2649.195756018162,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.824786412191915,
"min": 1.903725757958397,
"max": 3.9938355420796285,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2436.38894456625,
"min": 239.86944550275803,
"max": 2649.195756018162,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017580164287937804,
"min": 0.01368306062843961,
"max": 0.021293933304130205,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05274049286381341,
"min": 0.02736612125687922,
"max": 0.06388179991239061,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05760152406162686,
"min": 0.02240980723872781,
"max": 0.07115776271869739,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17280457218488057,
"min": 0.04481961447745562,
"max": 0.2002278607338667,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.902848699083322e-06,
"min": 3.902848699083322e-06,
"max": 0.0002953429515523499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1708546097249964e-05,
"min": 1.1708546097249964e-05,
"max": 0.0008443099685633499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10130091666666664,
"min": 0.10130091666666664,
"max": 0.19844764999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30390274999999994,
"min": 0.20773054999999999,
"max": 0.5814366499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.491574166666649e-05,
"min": 7.491574166666649e-05,
"max": 0.0049225377349999995,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022474722499999948,
"min": 0.00022474722499999948,
"max": 0.014073688834999999,
"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": "1716102305",
"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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1716104955"
},
"total": 2649.272025344,
"count": 1,
"self": 0.5981917320000321,
"children": {
"run_training.setup": {
"total": 0.05534987199996522,
"count": 1,
"self": 0.05534987199996522
},
"TrainerController.start_learning": {
"total": 2648.61848374,
"count": 1,
"self": 4.841521043961166,
"children": {
"TrainerController._reset_env": {
"total": 2.944901846999983,
"count": 1,
"self": 2.944901846999983
},
"TrainerController.advance": {
"total": 2640.7188733950384,
"count": 233326,
"self": 5.058405678919371,
"children": {
"env_step": {
"total": 2090.205015777025,
"count": 233326,
"self": 1730.681384707187,
"children": {
"SubprocessEnvManager._take_step": {
"total": 356.1053597367986,
"count": 233326,
"self": 18.237270825842188,
"children": {
"TorchPolicy.evaluate": {
"total": 337.86808891095643,
"count": 222971,
"self": 337.86808891095643
}
}
},
"workers": {
"total": 3.4182713330394563,
"count": 233326,
"self": 0.0,
"children": {
"worker_root": {
"total": 2640.956394910978,
"count": 233326,
"is_parallel": true,
"self": 1250.4905686829547,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000978952000082245,
"count": 1,
"is_parallel": true,
"self": 0.00029396300021744537,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006849889998647996,
"count": 2,
"is_parallel": true,
"self": 0.0006849889998647996
}
}
},
"UnityEnvironment.step": {
"total": 0.045513472000038746,
"count": 1,
"is_parallel": true,
"self": 0.0005232730001125674,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022284599992872245,
"count": 1,
"is_parallel": true,
"self": 0.00022284599992872245
},
"communicator.exchange": {
"total": 0.04376547699996536,
"count": 1,
"is_parallel": true,
"self": 0.04376547699996536
},
"steps_from_proto": {
"total": 0.001001876000032098,
"count": 1,
"is_parallel": true,
"self": 0.0002558869999802482,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007459890000518499,
"count": 2,
"is_parallel": true,
"self": 0.0007459890000518499
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1390.4658262280232,
"count": 233325,
"is_parallel": true,
"self": 41.052092686041306,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 89.82095646607172,
"count": 233325,
"is_parallel": true,
"self": 89.82095646607172
},
"communicator.exchange": {
"total": 1162.2038308740296,
"count": 233325,
"is_parallel": true,
"self": 1162.2038308740296
},
"steps_from_proto": {
"total": 97.38894620188046,
"count": 233325,
"is_parallel": true,
"self": 37.1528785578389,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.236067644041555,
"count": 466650,
"is_parallel": true,
"self": 60.236067644041555
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 545.455451939094,
"count": 233326,
"self": 7.057502406040612,
"children": {
"process_trajectory": {
"total": 175.40654980805425,
"count": 233326,
"self": 173.91550561405393,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4910441940003238,
"count": 10,
"self": 1.4910441940003238
}
}
},
"_update_policy": {
"total": 362.99139972499916,
"count": 97,
"self": 295.32612977898725,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.6652699460119,
"count": 2910,
"self": 67.6652699460119
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.140003385255113e-07,
"count": 1,
"self": 9.140003385255113e-07
},
"TrainerController._save_models": {
"total": 0.11318654000024253,
"count": 1,
"self": 0.0018014760003097763,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11138506399993275,
"count": 1,
"self": 0.11138506399993275
}
}
}
}
}
}
}