ppo-Huggy / run_logs /timers.json
HaochengLin656's picture
Huggy
41da99b verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4070675373077393,
"min": 1.4070675373077393,
"max": 1.4280903339385986,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69955.1796875,
"min": 68212.453125,
"max": 78966.171875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 93.2810707456979,
"min": 87.7921146953405,
"max": 417.78333333333336,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 48786.0,
"min": 48786.0,
"max": 50144.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999951.0,
"min": 49933.0,
"max": 1999951.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999951.0,
"min": 49933.0,
"max": 1999951.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.433748722076416,
"min": 0.10892074555158615,
"max": 2.4701175689697266,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1272.8505859375,
"min": 12.961568832397461,
"max": 1365.446533203125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8273371044354048,
"min": 1.9597367505315972,
"max": 3.905594036923892,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2001.6973056197166,
"min": 233.20867331326008,
"max": 2124.1000408530235,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8273371044354048,
"min": 1.9597367505315972,
"max": 3.905594036923892,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2001.6973056197166,
"min": 233.20867331326008,
"max": 2124.1000408530235,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014144179469440132,
"min": 0.013793812167326298,
"max": 0.019536686017818286,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.028288358938880265,
"min": 0.027587624334652595,
"max": 0.05662826739329224,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.055024615054329234,
"min": 0.021949862067898115,
"max": 0.06252035455157359,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.11004923010865847,
"min": 0.04389972413579623,
"max": 0.17996499240398406,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.584548471850001e-06,
"min": 4.584548471850001e-06,
"max": 0.000295369876543375,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.169096943700002e-06,
"min": 9.169096943700002e-06,
"max": 0.0008443689185436999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10152814999999997,
"min": 0.10152814999999997,
"max": 0.198456625,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20305629999999994,
"min": 0.20305629999999994,
"max": 0.5814563,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.625468499999999e-05,
"min": 8.625468499999999e-05,
"max": 0.0049229855875,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017250936999999998,
"min": 0.00017250936999999998,
"max": 0.01407466937,
"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": "1738755724",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1738758144"
},
"total": 2419.59310026,
"count": 1,
"self": 0.7476231169998755,
"children": {
"run_training.setup": {
"total": 0.022587933999943743,
"count": 1,
"self": 0.022587933999943743
},
"TrainerController.start_learning": {
"total": 2418.822889209,
"count": 1,
"self": 4.407563494982696,
"children": {
"TrainerController._reset_env": {
"total": 3.1402409099999886,
"count": 1,
"self": 3.1402409099999886
},
"TrainerController.advance": {
"total": 2411.100260125017,
"count": 231914,
"self": 4.59575527787274,
"children": {
"env_step": {
"total": 1914.8046750911553,
"count": 231914,
"self": 1492.0637309712706,
"children": {
"SubprocessEnvManager._take_step": {
"total": 420.1301805450023,
"count": 231914,
"self": 15.492411518013,
"children": {
"TorchPolicy.evaluate": {
"total": 404.6377690269893,
"count": 222890,
"self": 404.6377690269893
}
}
},
"workers": {
"total": 2.6107635748824123,
"count": 231914,
"self": 0.0,
"children": {
"worker_root": {
"total": 2411.383374013023,
"count": 231914,
"is_parallel": true,
"self": 1200.855698177027,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009608450000087032,
"count": 1,
"is_parallel": true,
"self": 0.0003475190000017392,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000613326000006964,
"count": 2,
"is_parallel": true,
"self": 0.000613326000006964
}
}
},
"UnityEnvironment.step": {
"total": 0.029415951000032692,
"count": 1,
"is_parallel": true,
"self": 0.0003011499999274747,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001876780000884537,
"count": 1,
"is_parallel": true,
"self": 0.0001876780000884537
},
"communicator.exchange": {
"total": 0.0282175830000142,
"count": 1,
"is_parallel": true,
"self": 0.0282175830000142
},
"steps_from_proto": {
"total": 0.000709540000002562,
"count": 1,
"is_parallel": true,
"self": 0.00020398999993176403,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000505550000070798,
"count": 2,
"is_parallel": true,
"self": 0.000505550000070798
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1210.527675835996,
"count": 231913,
"is_parallel": true,
"self": 37.45615338202515,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.1401831889915,
"count": 231913,
"is_parallel": true,
"self": 80.1401831889915
},
"communicator.exchange": {
"total": 1007.4910889450516,
"count": 231913,
"is_parallel": true,
"self": 1007.4910889450516
},
"steps_from_proto": {
"total": 85.44025031992771,
"count": 231913,
"is_parallel": true,
"self": 30.07291444272653,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.367335877201185,
"count": 463826,
"is_parallel": true,
"self": 55.367335877201185
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 491.69982975598896,
"count": 231914,
"self": 6.503726747945507,
"children": {
"process_trajectory": {
"total": 157.30269372004352,
"count": 231914,
"self": 155.85395701404366,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4487367059998633,
"count": 10,
"self": 1.4487367059998633
}
}
},
"_update_policy": {
"total": 327.89340928799993,
"count": 96,
"self": 261.74668694199727,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.14672234600266,
"count": 2880,
"self": 66.14672234600266
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1639999684120994e-06,
"count": 1,
"self": 1.1639999684120994e-06
},
"TrainerController._save_models": {
"total": 0.17482351500029836,
"count": 1,
"self": 0.0027196330001970637,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1721038820001013,
"count": 1,
"self": 0.1721038820001013
}
}
}
}
}
}
}