ppo-Huggy / run_logs /timers.json
chauvanphuoc's picture
Huggy
85aba47 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4013965129852295,
"min": 1.4013965129852295,
"max": 1.427093267440796,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70288.4453125,
"min": 68403.84375,
"max": 77045.1484375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 65.31962864721486,
"min": 65.31962864721486,
"max": 403.06451612903226,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49251.0,
"min": 49194.0,
"max": 49980.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999956.0,
"min": 49845.0,
"max": 1999956.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999956.0,
"min": 49845.0,
"max": 1999956.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.526137590408325,
"min": 0.1542666107416153,
"max": 2.6297037601470947,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1904.707763671875,
"min": 18.97479248046875,
"max": 1911.32666015625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.936282376553715,
"min": 1.7701452757284892,
"max": 4.153737978755751,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2967.956911921501,
"min": 217.7278689146042,
"max": 2990.862661063671,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.936282376553715,
"min": 1.7701452757284892,
"max": 4.153737978755751,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2967.956911921501,
"min": 217.7278689146042,
"max": 2990.862661063671,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016386166077184804,
"min": 0.014547585776017514,
"max": 0.019373997863537322,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04915849823155441,
"min": 0.02993631422965943,
"max": 0.05331435342086479,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06018691414760219,
"min": 0.022301253365973633,
"max": 0.06633943772564332,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18056074244280657,
"min": 0.04460250673194727,
"max": 0.18590752482414247,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.913848695416661e-06,
"min": 3.913848695416661e-06,
"max": 0.00029529427656857494,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1741546086249984e-05,
"min": 1.1741546086249984e-05,
"max": 0.00084383296872235,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10130458333333332,
"min": 0.10130458333333332,
"max": 0.198431425,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30391375,
"min": 0.20773424999999995,
"max": 0.58127765,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.509870833333322e-05,
"min": 7.509870833333322e-05,
"max": 0.004921728107499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022529612499999966,
"min": 0.00022529612499999966,
"max": 0.014065754735000002,
"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": "1764950163",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/phuoccv/miniconda3/envs/mlenv/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./training-envs-executables/linux/Huggy/Huggy.x86_64 --run-id=Huggy2 --no-graphics --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1764950886"
},
"total": 722.1670381540025,
"count": 1,
"self": 0.16635941300773993,
"children": {
"run_training.setup": {
"total": 0.012320176989305764,
"count": 1,
"self": 0.012320176989305764
},
"TrainerController.start_learning": {
"total": 721.9883585640055,
"count": 1,
"self": 1.7315197090210859,
"children": {
"TrainerController._reset_env": {
"total": 0.9070623110164888,
"count": 1,
"self": 0.9070623110164888
},
"TrainerController.advance": {
"total": 719.3139233589463,
"count": 233786,
"self": 1.7104575042030774,
"children": {
"env_step": {
"total": 557.1800134710502,
"count": 233786,
"self": 425.58322522285744,
"children": {
"SubprocessEnvManager._take_step": {
"total": 130.44343875267077,
"count": 233786,
"self": 6.221966921904823,
"children": {
"TorchPolicy.evaluate": {
"total": 124.22147183076595,
"count": 222902,
"self": 124.22147183076595
}
}
},
"workers": {
"total": 1.1533494955219794,
"count": 233786,
"self": 0.0,
"children": {
"worker_root": {
"total": 719.901969079976,
"count": 233786,
"is_parallel": true,
"self": 385.18711897404864,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0004740770091302693,
"count": 1,
"is_parallel": true,
"self": 0.00012949699885211885,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00034458001027815044,
"count": 2,
"is_parallel": true,
"self": 0.00034458001027815044
}
}
},
"UnityEnvironment.step": {
"total": 0.010319619002984837,
"count": 1,
"is_parallel": true,
"self": 7.349997758865356e-05,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 9.951600804924965e-05,
"count": 1,
"is_parallel": true,
"self": 9.951600804924965e-05
},
"communicator.exchange": {
"total": 0.009975355991628021,
"count": 1,
"is_parallel": true,
"self": 0.009975355991628021
},
"steps_from_proto": {
"total": 0.00017124702571891248,
"count": 1,
"is_parallel": true,
"self": 4.841500776819885e-05,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00012283201795071363,
"count": 2,
"is_parallel": true,
"self": 0.00012283201795071363
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 334.7148501059273,
"count": 233785,
"is_parallel": true,
"self": 10.19089581471053,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 18.549772936006775,
"count": 233785,
"is_parallel": true,
"self": 18.549772936006775
},
"communicator.exchange": {
"total": 282.8582072025165,
"count": 233785,
"is_parallel": true,
"self": 282.8582072025165
},
"steps_from_proto": {
"total": 23.115974152693525,
"count": 233785,
"is_parallel": true,
"self": 8.03469406804652,
"children": {
"_process_rank_one_or_two_observation": {
"total": 15.081280084647005,
"count": 467570,
"is_parallel": true,
"self": 15.081280084647005
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 160.42345238369307,
"count": 233786,
"self": 2.383431712689344,
"children": {
"process_trajectory": {
"total": 59.575145739043364,
"count": 233786,
"self": 59.15575556104886,
"children": {
"RLTrainer._checkpoint": {
"total": 0.41939017799450085,
"count": 10,
"self": 0.41939017799450085
}
}
},
"_update_policy": {
"total": 98.46487493196037,
"count": 97,
"self": 81.95862112354371,
"children": {
"TorchPPOOptimizer.update": {
"total": 16.50625380841666,
"count": 2910,
"self": 16.50625380841666
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.320172592997551e-07,
"count": 1,
"self": 4.320172592997551e-07
},
"TrainerController._save_models": {
"total": 0.035852753004292026,
"count": 1,
"self": 0.000560031010536477,
"children": {
"RLTrainer._checkpoint": {
"total": 0.03529272199375555,
"count": 1,
"self": 0.03529272199375555
}
}
}
}
}
}
}