ppo-Huggy / run_logs /timers.json
mmek's picture
Huggy
fb1a65e
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4046303033828735,
"min": 1.4046303033828735,
"max": 1.4269152879714966,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70772.296875,
"min": 68464.703125,
"max": 78065.7265625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 90.52833638025594,
"min": 90.22627737226277,
"max": 405.6666666666667,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49519.0,
"min": 48941.0,
"max": 50036.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999343.0,
"min": 49994.0,
"max": 1999343.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999343.0,
"min": 49994.0,
"max": 1999343.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3952789306640625,
"min": 0.08867943286895752,
"max": 2.4514501094818115,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1310.217529296875,
"min": 10.818890571594238,
"max": 1310.3106689453125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6741511018664137,
"min": 1.833883725961701,
"max": 3.971043285490437,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2009.7606527209282,
"min": 223.7338145673275,
"max": 2128.176730453968,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6741511018664137,
"min": 1.833883725961701,
"max": 3.971043285490437,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2009.7606527209282,
"min": 223.7338145673275,
"max": 2128.176730453968,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.011963237393906133,
"min": 0.011963237393906133,
"max": 0.019900955526585072,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0358897121817184,
"min": 0.027670892422399142,
"max": 0.05723523387569003,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05602793871528572,
"min": 0.021077943593263627,
"max": 0.056036401622825194,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16808381614585716,
"min": 0.042155887186527255,
"max": 0.16810920486847558,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.284098905333342e-06,
"min": 3.284098905333342e-06,
"max": 0.00029536327654557494,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.852296716000026e-06,
"min": 9.852296716000026e-06,
"max": 0.0008441701686099499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10109466666666665,
"min": 0.10109466666666665,
"max": 0.198454425,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30328399999999994,
"min": 0.2073867000000001,
"max": 0.5813900500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.462386666666681e-05,
"min": 6.462386666666681e-05,
"max": 0.004922875807500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019387160000000045,
"min": 0.00019387160000000045,
"max": 0.014071363495000004,
"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": "1699543694",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1699546186"
},
"total": 2492.1405613340003,
"count": 1,
"self": 0.40033410799969715,
"children": {
"run_training.setup": {
"total": 0.043411018000142576,
"count": 1,
"self": 0.043411018000142576
},
"TrainerController.start_learning": {
"total": 2491.696816208,
"count": 1,
"self": 4.9178407461299685,
"children": {
"TrainerController._reset_env": {
"total": 7.834415542999977,
"count": 1,
"self": 7.834415542999977
},
"TrainerController.advance": {
"total": 2478.8376764558698,
"count": 231820,
"self": 5.008628400963971,
"children": {
"env_step": {
"total": 1969.184658762916,
"count": 231820,
"self": 1622.136168500747,
"children": {
"SubprocessEnvManager._take_step": {
"total": 344.0205235090782,
"count": 231820,
"self": 17.09898076799982,
"children": {
"TorchPolicy.evaluate": {
"total": 326.9215427410784,
"count": 222975,
"self": 326.9215427410784
}
}
},
"workers": {
"total": 3.0279667530905954,
"count": 231820,
"self": 0.0,
"children": {
"worker_root": {
"total": 2483.950671055093,
"count": 231820,
"is_parallel": true,
"self": 1168.7839341531965,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008036619999529648,
"count": 1,
"is_parallel": true,
"self": 0.00021819900007358228,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005854629998793826,
"count": 2,
"is_parallel": true,
"self": 0.0005854629998793826
}
}
},
"UnityEnvironment.step": {
"total": 0.03394075199980762,
"count": 1,
"is_parallel": true,
"self": 0.0003448429997661151,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000240542000028654,
"count": 1,
"is_parallel": true,
"self": 0.000240542000028654
},
"communicator.exchange": {
"total": 0.03263972299987472,
"count": 1,
"is_parallel": true,
"self": 0.03263972299987472
},
"steps_from_proto": {
"total": 0.000715644000138127,
"count": 1,
"is_parallel": true,
"self": 0.00019668600020850135,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005189579999296257,
"count": 2,
"is_parallel": true,
"self": 0.0005189579999296257
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1315.1667369018967,
"count": 231819,
"is_parallel": true,
"self": 40.98478007392873,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.61782518493715,
"count": 231819,
"is_parallel": true,
"self": 86.61782518493715
},
"communicator.exchange": {
"total": 1093.9745847289528,
"count": 231819,
"is_parallel": true,
"self": 1093.9745847289528
},
"steps_from_proto": {
"total": 93.58954691407803,
"count": 231819,
"is_parallel": true,
"self": 34.521129398118546,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.06841751595948,
"count": 463638,
"is_parallel": true,
"self": 59.06841751595948
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 504.6443892919897,
"count": 231820,
"self": 7.138492405947545,
"children": {
"process_trajectory": {
"total": 156.88678836104282,
"count": 231820,
"self": 155.70474492504286,
"children": {
"RLTrainer._checkpoint": {
"total": 1.182043435999958,
"count": 10,
"self": 1.182043435999958
}
}
},
"_update_policy": {
"total": 340.6191085249993,
"count": 97,
"self": 278.0673945089841,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.55171401601524,
"count": 2910,
"self": 62.55171401601524
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0090002433571499e-06,
"count": 1,
"self": 1.0090002433571499e-06
},
"TrainerController._save_models": {
"total": 0.10688245400024243,
"count": 1,
"self": 0.00204410300057134,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10483835099967109,
"count": 1,
"self": 0.10483835099967109
}
}
}
}
}
}
}