ppo-Huggy / run_logs /timers.json
FilBr's picture
Huggy
689dcb3 verified
Raw
History Blame Contribute Delete
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4038019180297852,
"min": 1.4038019180297852,
"max": 1.4048850536346436,
"count": 7
},
"Huggy.Policy.Entropy.sum": {
"value": 70546.6640625,
"min": 19459.0625,
"max": 70770.359375,
"count": 7
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 78.16031746031746,
"min": 66.86153846153846,
"max": 78.16031746031746,
"count": 7
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49241.0,
"min": 13038.0,
"max": 49419.0,
"count": 7
},
"Huggy.Step.mean": {
"value": 1999976.0,
"min": 1699934.0,
"max": 1999976.0,
"count": 7
},
"Huggy.Step.sum": {
"value": 1999976.0,
"min": 1699934.0,
"max": 1999976.0,
"count": 7
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4777321815490723,
"min": 2.421337366104126,
"max": 2.49997615814209,
"count": 7
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1560.9713134765625,
"min": 484.9953918457031,
"max": 1703.270263671875,
"count": 7
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.923013033469518,
"min": 3.702766056835037,
"max": 3.960184207357512,
"count": 7
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2471.4982110857964,
"min": 718.3366150259972,
"max": 2688.514925301075,
"count": 7
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.923013033469518,
"min": 3.702766056835037,
"max": 3.960184207357512,
"count": 7
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2471.4982110857964,
"min": 718.3366150259972,
"max": 2688.514925301075,
"count": 7
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 7
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 7
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017824621167124455,
"min": 0.014529805911782509,
"max": 0.019127288927039545,
"count": 6
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05347386350137337,
"min": 0.029059611823565017,
"max": 0.05738186678111863,
"count": 6
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0606815586073531,
"min": 0.060388369527128005,
"max": 0.06719341716832584,
"count": 6
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1820446758220593,
"min": 0.12472081656257311,
"max": 0.20158025150497755,
"count": 6
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.879398706899997e-06,
"min": 3.879398706899997e-06,
"max": 4.082808639066667e-05,
"count": 6
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.163819612069999e-05,
"min": 1.163819612069999e-05,
"max": 0.000122484259172,
"count": 6
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10129309999999998,
"min": 0.10129309999999998,
"max": 0.11360933333333334,
"count": 6
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30387929999999996,
"min": 0.20772680000000004,
"max": 0.340828,
"count": 6
},
"Huggy.Policy.Beta.mean": {
"value": 7.452568999999995e-05,
"min": 7.452568999999995e-05,
"max": 0.0006891057333333334,
"count": 6
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022357706999999983,
"min": 0.00022357706999999983,
"max": 0.0020673172,
"count": 6
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1717242738",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/filbr/miniconda3/envs/huggy/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics --resume",
"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": "1717242960"
},
"total": 222.36291325899992,
"count": 1,
"self": 0.37086419399975057,
"children": {
"run_training.setup": {
"total": 0.037123995999991166,
"count": 1,
"self": 0.037123995999991166
},
"TrainerController.start_learning": {
"total": 221.95492506900018,
"count": 1,
"self": 0.4127531910471589,
"children": {
"TrainerController._reset_env": {
"total": 2.711735258000317,
"count": 1,
"self": 2.711735258000317
},
"TrainerController.advance": {
"total": 218.62760177695282,
"count": 37059,
"self": 0.398634579042664,
"children": {
"env_step": {
"total": 177.67429402997595,
"count": 37059,
"self": 125.35822976988675,
"children": {
"SubprocessEnvManager._take_step": {
"total": 52.03270441603445,
"count": 37059,
"self": 1.4074412080199181,
"children": {
"TorchPolicy.evaluate": {
"total": 50.62526320801453,
"count": 35100,
"self": 50.62526320801453
}
}
},
"workers": {
"total": 0.28335984405475756,
"count": 37059,
"self": 0.0,
"children": {
"worker_root": {
"total": 220.72467764199382,
"count": 37059,
"is_parallel": true,
"self": 116.44044387702706,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0004602909998538962,
"count": 1,
"is_parallel": true,
"self": 0.00013729099964621128,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00032300000020768493,
"count": 2,
"is_parallel": true,
"self": 0.00032300000020768493
}
}
},
"UnityEnvironment.step": {
"total": 0.011376243000086106,
"count": 1,
"is_parallel": true,
"self": 8.948100003181025e-05,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.271100002981257e-05,
"count": 1,
"is_parallel": true,
"self": 7.271100002981257e-05
},
"communicator.exchange": {
"total": 0.011019917999874451,
"count": 1,
"is_parallel": true,
"self": 0.011019917999874451
},
"steps_from_proto": {
"total": 0.00019413300015003188,
"count": 1,
"is_parallel": true,
"self": 5.311800032359315e-05,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00014101499982643872,
"count": 2,
"is_parallel": true,
"self": 0.00014101499982643872
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 104.28423376496676,
"count": 37058,
"is_parallel": true,
"self": 2.145334870966053,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.3925846490278673,
"count": 37058,
"is_parallel": true,
"self": 3.3925846490278673
},
"communicator.exchange": {
"total": 94.22722936099171,
"count": 37058,
"is_parallel": true,
"self": 94.22722936099171
},
"steps_from_proto": {
"total": 4.519084883981122,
"count": 37058,
"is_parallel": true,
"self": 1.4193934280297071,
"children": {
"_process_rank_one_or_two_observation": {
"total": 3.0996914559514153,
"count": 74116,
"is_parallel": true,
"self": 3.0996914559514153
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 40.5546731679342,
"count": 37059,
"self": 0.6097072929328533,
"children": {
"process_trajectory": {
"total": 17.53491911600122,
"count": 37059,
"self": 17.197197691001293,
"children": {
"RLTrainer._checkpoint": {
"total": 0.33772142499992697,
"count": 2,
"self": 0.33772142499992697
}
}
},
"_update_policy": {
"total": 22.410046759000124,
"count": 15,
"self": 14.888752356003806,
"children": {
"TorchPPOOptimizer.update": {
"total": 7.521294402996318,
"count": 450,
"self": 7.521294402996318
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.5100023271515965e-07,
"count": 1,
"self": 4.5100023271515965e-07
},
"TrainerController._save_models": {
"total": 0.2028343919996587,
"count": 1,
"self": 0.05375839399948745,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14907599800017124,
"count": 1,
"self": 0.14907599800017124
}
}
}
}
}
}
}