ppo-Huggy / run_logs /timers.json
nbiish's picture
Unit 1 Bonus
ca115cb
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4116761684417725,
"min": 1.4116761684417725,
"max": 1.4270844459533691,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70890.140625,
"min": 69022.046875,
"max": 77988.875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 78.6782334384858,
"min": 76.35625,
"max": 402.41129032258067,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49882.0,
"min": 48868.0,
"max": 50246.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999706.0,
"min": 49786.0,
"max": 1999706.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999706.0,
"min": 49786.0,
"max": 1999706.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4798285961151123,
"min": 0.04251154512166977,
"max": 2.480151891708374,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1569.7314453125,
"min": 5.228919982910156,
"max": 1582.3369140625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.835258182379495,
"min": 1.6753825240018891,
"max": 3.9484754921776233,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2427.7184294462204,
"min": 206.07205045223236,
"max": 2468.8526154756546,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.835258182379495,
"min": 1.6753825240018891,
"max": 3.9484754921776233,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2427.7184294462204,
"min": 206.07205045223236,
"max": 2468.8526154756546,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01872260838540064,
"min": 0.011636718942706164,
"max": 0.021551961215057723,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05616782515620192,
"min": 0.023273437885412328,
"max": 0.061085885411133245,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06142859798338678,
"min": 0.02226653524364034,
"max": 0.06142859798338678,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18428579395016034,
"min": 0.04453307048728068,
"max": 0.18428579395016034,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5493488169166596e-06,
"min": 3.5493488169166596e-06,
"max": 0.00029531625156125,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0648046450749978e-05,
"min": 1.0648046450749978e-05,
"max": 0.0008441100186299998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10118308333333335,
"min": 0.10118308333333335,
"max": 0.19843874999999994,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30354925000000005,
"min": 0.2074949,
"max": 0.5813699999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.903585833333322e-05,
"min": 6.903585833333322e-05,
"max": 0.004922093625,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020710757499999965,
"min": 0.00020710757499999965,
"max": 0.014070363,
"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": "1686797957",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"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": "1686800708"
},
"total": 2750.3000084910004,
"count": 1,
"self": 0.8422153350006738,
"children": {
"run_training.setup": {
"total": 0.04302305700002762,
"count": 1,
"self": 0.04302305700002762
},
"TrainerController.start_learning": {
"total": 2749.4147700989997,
"count": 1,
"self": 5.826037883910885,
"children": {
"TrainerController._reset_env": {
"total": 4.150613745000101,
"count": 1,
"self": 4.150613745000101
},
"TrainerController.advance": {
"total": 2739.2358269550896,
"count": 232616,
"self": 5.854553461057094,
"children": {
"env_step": {
"total": 2166.840780196099,
"count": 232616,
"self": 1818.4860988421979,
"children": {
"SubprocessEnvManager._take_step": {
"total": 344.5475830349169,
"count": 232616,
"self": 19.949828778886967,
"children": {
"TorchPolicy.evaluate": {
"total": 324.59775425602993,
"count": 222934,
"self": 324.59775425602993
}
}
},
"workers": {
"total": 3.807098318984117,
"count": 232616,
"self": 0.0,
"children": {
"worker_root": {
"total": 2739.8106887351573,
"count": 232616,
"is_parallel": true,
"self": 1267.5412461171977,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009488360001341789,
"count": 1,
"is_parallel": true,
"self": 0.0002852899999652436,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006635460001689353,
"count": 2,
"is_parallel": true,
"self": 0.0006635460001689353
}
}
},
"UnityEnvironment.step": {
"total": 0.0385931260000234,
"count": 1,
"is_parallel": true,
"self": 0.000368404000028022,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00025274799986618746,
"count": 1,
"is_parallel": true,
"self": 0.00025274799986618746
},
"communicator.exchange": {
"total": 0.037161150999963866,
"count": 1,
"is_parallel": true,
"self": 0.037161150999963866
},
"steps_from_proto": {
"total": 0.0008108230001653283,
"count": 1,
"is_parallel": true,
"self": 0.00024188400016100786,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005689390000043204,
"count": 2,
"is_parallel": true,
"self": 0.0005689390000043204
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1472.2694426179596,
"count": 232615,
"is_parallel": true,
"self": 43.587009670057796,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.61409596094063,
"count": 232615,
"is_parallel": true,
"self": 86.61409596094063
},
"communicator.exchange": {
"total": 1233.1713257540205,
"count": 232615,
"is_parallel": true,
"self": 1233.1713257540205
},
"steps_from_proto": {
"total": 108.89701123294071,
"count": 232615,
"is_parallel": true,
"self": 39.86259307988507,
"children": {
"_process_rank_one_or_two_observation": {
"total": 69.03441815305564,
"count": 465230,
"is_parallel": true,
"self": 69.03441815305564
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 566.5404932979336,
"count": 232616,
"self": 8.743774302874272,
"children": {
"process_trajectory": {
"total": 152.46019113305783,
"count": 232616,
"self": 151.09615846805832,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3640326649995131,
"count": 10,
"self": 1.3640326649995131
}
}
},
"_update_policy": {
"total": 405.3365278620015,
"count": 97,
"self": 342.1727594620022,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.1637683999993,
"count": 2910,
"self": 63.1637683999993
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1839993021567352e-06,
"count": 1,
"self": 1.1839993021567352e-06
},
"TrainerController._save_models": {
"total": 0.20229033099985827,
"count": 1,
"self": 0.0029647069995917263,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19932562400026654,
"count": 1,
"self": 0.19932562400026654
}
}
}
}
}
}
}