ppo-Huggy / run_logs /timers.json
stillerman's picture
Huggy
dbccc3b
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4052058458328247,
"min": 1.405196189880371,
"max": 1.4289779663085938,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70389.5703125,
"min": 67319.609375,
"max": 77257.546875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 118.5107398568019,
"min": 85.41680960548885,
"max": 397.73809523809524,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49656.0,
"min": 49061.0,
"max": 50131.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999977.0,
"min": 49852.0,
"max": 1999977.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999977.0,
"min": 49852.0,
"max": 1999977.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3308894634246826,
"min": 0.04203926399350166,
"max": 2.441765785217285,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 976.6427001953125,
"min": 5.254908084869385,
"max": 1423.5494384765625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.517546011183882,
"min": 1.7560807373523712,
"max": 3.853624871135622,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1473.8517786860466,
"min": 219.5100921690464,
"max": 2184.032427608967,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.517546011183882,
"min": 1.7560807373523712,
"max": 3.853624871135622,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1473.8517786860466,
"min": 219.5100921690464,
"max": 2184.032427608967,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01734945809455692,
"min": 0.013237527798628435,
"max": 0.020216214753842603,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05204837428367076,
"min": 0.028773792915550683,
"max": 0.05762480510287181,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.041436355850762795,
"min": 0.022622768549869457,
"max": 0.0570825632661581,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.12430906755228838,
"min": 0.045245537099738914,
"max": 0.16563406884670256,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.220898926399991e-06,
"min": 3.220898926399991e-06,
"max": 0.00029532187655937497,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.662696779199973e-06,
"min": 9.662696779199973e-06,
"max": 0.0008442109685963498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10107359999999999,
"min": 0.10107359999999999,
"max": 0.19844062500000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30322079999999996,
"min": 0.20731365000000004,
"max": 0.58140365,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.357263999999986e-05,
"min": 6.357263999999986e-05,
"max": 0.0049221871875,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019071791999999957,
"min": 0.00019071791999999957,
"max": 0.014072042134999999,
"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": "1695325009",
"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": "1695327538"
},
"total": 2528.962004539,
"count": 1,
"self": 0.4408650650002528,
"children": {
"run_training.setup": {
"total": 0.04630321499996626,
"count": 1,
"self": 0.04630321499996626
},
"TrainerController.start_learning": {
"total": 2528.474836259,
"count": 1,
"self": 4.664558764992762,
"children": {
"TrainerController._reset_env": {
"total": 4.310863436000091,
"count": 1,
"self": 4.310863436000091
},
"TrainerController.advance": {
"total": 2519.3772348790067,
"count": 231843,
"self": 4.817328626129438,
"children": {
"env_step": {
"total": 1943.8056802068916,
"count": 231843,
"self": 1645.6706586888245,
"children": {
"SubprocessEnvManager._take_step": {
"total": 295.0834507490026,
"count": 231843,
"self": 16.67645845402808,
"children": {
"TorchPolicy.evaluate": {
"total": 278.40699229497454,
"count": 223091,
"self": 278.40699229497454
}
}
},
"workers": {
"total": 3.051570769064483,
"count": 231843,
"self": 0.0,
"children": {
"worker_root": {
"total": 2520.939154607083,
"count": 231843,
"is_parallel": true,
"self": 1174.4187938251803,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010143060000018522,
"count": 1,
"is_parallel": true,
"self": 0.000285551000047235,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007287549999546172,
"count": 2,
"is_parallel": true,
"self": 0.0007287549999546172
}
}
},
"UnityEnvironment.step": {
"total": 0.030015387999924314,
"count": 1,
"is_parallel": true,
"self": 0.0003782979999868985,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00024403600002642634,
"count": 1,
"is_parallel": true,
"self": 0.00024403600002642634
},
"communicator.exchange": {
"total": 0.028581823999957123,
"count": 1,
"is_parallel": true,
"self": 0.028581823999957123
},
"steps_from_proto": {
"total": 0.0008112299999538664,
"count": 1,
"is_parallel": true,
"self": 0.00022278299991285166,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005884470000410147,
"count": 2,
"is_parallel": true,
"self": 0.0005884470000410147
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1346.5203607819026,
"count": 231842,
"is_parallel": true,
"self": 40.760297239871534,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.41368493203231,
"count": 231842,
"is_parallel": true,
"self": 83.41368493203231
},
"communicator.exchange": {
"total": 1120.9277862959384,
"count": 231842,
"is_parallel": true,
"self": 1120.9277862959384
},
"steps_from_proto": {
"total": 101.41859231406033,
"count": 231842,
"is_parallel": true,
"self": 35.629834521063685,
"children": {
"_process_rank_one_or_two_observation": {
"total": 65.78875779299665,
"count": 463684,
"is_parallel": true,
"self": 65.78875779299665
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 570.7542260459857,
"count": 231843,
"self": 6.933291437995763,
"children": {
"process_trajectory": {
"total": 142.56375362198946,
"count": 231843,
"self": 141.0371370459892,
"children": {
"RLTrainer._checkpoint": {
"total": 1.526616576000265,
"count": 10,
"self": 1.526616576000265
}
}
},
"_update_policy": {
"total": 421.25718098600044,
"count": 97,
"self": 358.97514403399896,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.28203695200148,
"count": 2910,
"self": 62.28203695200148
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0550002116360702e-06,
"count": 1,
"self": 1.0550002116360702e-06
},
"TrainerController._save_models": {
"total": 0.12217812400012917,
"count": 1,
"self": 0.0019313160000820062,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12024680800004717,
"count": 1,
"self": 0.12024680800004717
}
}
}
}
}
}
}