ppo-Huggy / run_logs /timers.json
MrPio's picture
Huggy
94397a4 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4040721654891968,
"min": 1.4040721654891968,
"max": 1.432839274406433,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69335.890625,
"min": 68917.5390625,
"max": 78053.4921875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 86.8804920913884,
"min": 80.83469721767594,
"max": 378.7218045112782,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49435.0,
"min": 48821.0,
"max": 50370.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999917.0,
"min": 49817.0,
"max": 1999917.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999917.0,
"min": 49817.0,
"max": 1999917.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4855175018310547,
"min": 0.1605553925037384,
"max": 2.5116090774536133,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1414.259521484375,
"min": 21.19331169128418,
"max": 1517.0118408203125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.824389325975324,
"min": 1.7591310315059894,
"max": 3.9210270315606075,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2176.0775264799595,
"min": 232.2052961587906,
"max": 2368.300327062607,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.824389325975324,
"min": 1.7591310315059894,
"max": 3.9210270315606075,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2176.0775264799595,
"min": 232.2052961587906,
"max": 2368.300327062607,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01594071863995244,
"min": 0.013916211185217738,
"max": 0.019254181079062013,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04782215591985732,
"min": 0.027832422370435476,
"max": 0.054212104295417396,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06525780016349421,
"min": 0.01790691550510625,
"max": 0.06525780016349421,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.19577340049048264,
"min": 0.0358138310102125,
"max": 0.19577340049048264,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.572948809050005e-06,
"min": 3.572948809050005e-06,
"max": 0.00029531947656017494,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0718846427150015e-05,
"min": 1.0718846427150015e-05,
"max": 0.0008441727186090998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10119095000000004,
"min": 0.10119095000000004,
"max": 0.19843982500000007,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3035728500000001,
"min": 0.20757674999999998,
"max": 0.5813908999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.942840500000009e-05,
"min": 6.942840500000009e-05,
"max": 0.0049221472675,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020828521500000025,
"min": 0.00020828521500000025,
"max": 0.014071405910000001,
"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": "1709975762",
"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": "1709978254"
},
"total": 2491.790272226,
"count": 1,
"self": 0.7066728539998621,
"children": {
"run_training.setup": {
"total": 0.053529670000045826,
"count": 1,
"self": 0.053529670000045826
},
"TrainerController.start_learning": {
"total": 2491.030069702,
"count": 1,
"self": 4.445291377075591,
"children": {
"TrainerController._reset_env": {
"total": 3.1435595269999794,
"count": 1,
"self": 3.1435595269999794
},
"TrainerController.advance": {
"total": 2483.2646635299247,
"count": 232490,
"self": 4.916506456951993,
"children": {
"env_step": {
"total": 1997.818109300946,
"count": 232490,
"self": 1655.44731543007,
"children": {
"SubprocessEnvManager._take_step": {
"total": 339.4015754420145,
"count": 232490,
"self": 17.770162207035696,
"children": {
"TorchPolicy.evaluate": {
"total": 321.6314132349788,
"count": 222818,
"self": 321.6314132349788
}
}
},
"workers": {
"total": 2.9692184288614385,
"count": 232490,
"self": 0.0,
"children": {
"worker_root": {
"total": 2483.5509404279637,
"count": 232490,
"is_parallel": true,
"self": 1152.5388647739978,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001216084999953182,
"count": 1,
"is_parallel": true,
"self": 0.0003979520000143566,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008181329999388254,
"count": 2,
"is_parallel": true,
"self": 0.0008181329999388254
}
}
},
"UnityEnvironment.step": {
"total": 0.03089155899999696,
"count": 1,
"is_parallel": true,
"self": 0.0003656940000382747,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021731799995450274,
"count": 1,
"is_parallel": true,
"self": 0.00021731799995450274
},
"communicator.exchange": {
"total": 0.029523580999978094,
"count": 1,
"is_parallel": true,
"self": 0.029523580999978094
},
"steps_from_proto": {
"total": 0.0007849660000260883,
"count": 1,
"is_parallel": true,
"self": 0.00020316400002684532,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000581801999999243,
"count": 2,
"is_parallel": true,
"self": 0.000581801999999243
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1331.012075653966,
"count": 232489,
"is_parallel": true,
"self": 39.86701935611791,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.78698953090014,
"count": 232489,
"is_parallel": true,
"self": 84.78698953090014
},
"communicator.exchange": {
"total": 1113.3102022190562,
"count": 232489,
"is_parallel": true,
"self": 1113.3102022190562
},
"steps_from_proto": {
"total": 93.04786454789149,
"count": 232489,
"is_parallel": true,
"self": 34.71430001382947,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.33356453406202,
"count": 464978,
"is_parallel": true,
"self": 58.33356453406202
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 480.5300477720269,
"count": 232490,
"self": 6.89942286801363,
"children": {
"process_trajectory": {
"total": 160.60359032601394,
"count": 232490,
"self": 159.32109553801473,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2824947879992123,
"count": 10,
"self": 1.2824947879992123
}
}
},
"_update_policy": {
"total": 313.0270345779993,
"count": 97,
"self": 250.67559387400365,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.35144070399565,
"count": 2910,
"self": 62.35144070399565
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2880000213044696e-06,
"count": 1,
"self": 1.2880000213044696e-06
},
"TrainerController._save_models": {
"total": 0.17655397999988054,
"count": 1,
"self": 0.002863169000193011,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17369081099968753,
"count": 1,
"self": 0.17369081099968753
}
}
}
}
}
}
}