ppo-Huggy / run_logs /timers.json
jjlira's picture
Huggy
46a0a16
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4081617593765259,
"min": 1.4081617593765259,
"max": 1.427756905555725,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71282.5546875,
"min": 68812.0234375,
"max": 78321.9140625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 95.02687140115164,
"min": 88.17857142857143,
"max": 416.4793388429752,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49509.0,
"min": 48885.0,
"max": 50394.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999903.0,
"min": 49914.0,
"max": 1999903.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999903.0,
"min": 49914.0,
"max": 1999903.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4330132007598877,
"min": -0.025370784103870392,
"max": 2.455601692199707,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1267.599853515625,
"min": -3.044494152069092,
"max": 1331.946533203125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.732221356280248,
"min": 1.784370422611634,
"max": 3.977215995609542,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1944.4873266220093,
"min": 214.12445071339607,
"max": 2202.1103392243385,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.732221356280248,
"min": 1.784370422611634,
"max": 3.977215995609542,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1944.4873266220093,
"min": 214.12445071339607,
"max": 2202.1103392243385,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015651424105615458,
"min": 0.013579558761557564,
"max": 0.01975710812516304,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.046954272316846374,
"min": 0.027159117523115128,
"max": 0.05927132437548911,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.058547069422072835,
"min": 0.023455513641238213,
"max": 0.06301648124224611,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1756412082662185,
"min": 0.046911027282476425,
"max": 0.18904944372673832,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.1283489572499986e-06,
"min": 3.1283489572499986e-06,
"max": 0.00029534025155324997,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.385046871749995e-06,
"min": 9.385046871749995e-06,
"max": 0.0008439564186811997,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10104275,
"min": 0.10104275,
"max": 0.19844675,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30312825,
"min": 0.2072660500000001,
"max": 0.5813187999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.203322499999999e-05,
"min": 6.203322499999999e-05,
"max": 0.004922492824999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00018609967499999997,
"min": 0.00018609967499999997,
"max": 0.014067808120000002,
"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": "1677077136",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1677079471"
},
"total": 2334.943745334,
"count": 1,
"self": 0.6939514889995735,
"children": {
"run_training.setup": {
"total": 0.11480976500001816,
"count": 1,
"self": 0.11480976500001816
},
"TrainerController.start_learning": {
"total": 2334.1349840800003,
"count": 1,
"self": 4.070052863013643,
"children": {
"TrainerController._reset_env": {
"total": 11.680452065999987,
"count": 1,
"self": 11.680452065999987
},
"TrainerController.advance": {
"total": 2318.205412748987,
"count": 231819,
"self": 4.388783759063244,
"children": {
"env_step": {
"total": 1807.4128729480346,
"count": 231819,
"self": 1509.3660683270189,
"children": {
"SubprocessEnvManager._take_step": {
"total": 295.4046035019851,
"count": 231819,
"self": 15.60618074298867,
"children": {
"TorchPolicy.evaluate": {
"total": 279.7984227589964,
"count": 222988,
"self": 69.72975200599143,
"children": {
"TorchPolicy.sample_actions": {
"total": 210.068670753005,
"count": 222988,
"self": 210.068670753005
}
}
}
}
},
"workers": {
"total": 2.6422011190307444,
"count": 231819,
"self": 0.0,
"children": {
"worker_root": {
"total": 2325.6817799049777,
"count": 231819,
"is_parallel": true,
"self": 1096.4036621600071,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002047100000027058,
"count": 1,
"is_parallel": true,
"self": 0.00045101000000613567,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015960900000209222,
"count": 2,
"is_parallel": true,
"self": 0.0015960900000209222
}
}
},
"UnityEnvironment.step": {
"total": 0.05609430199996268,
"count": 1,
"is_parallel": true,
"self": 0.00029849899988221296,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020299500005194204,
"count": 1,
"is_parallel": true,
"self": 0.00020299500005194204
},
"communicator.exchange": {
"total": 0.05464065000001028,
"count": 1,
"is_parallel": true,
"self": 0.05464065000001028
},
"steps_from_proto": {
"total": 0.0009521580000182439,
"count": 1,
"is_parallel": true,
"self": 0.0004837309999743411,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004684270000439028,
"count": 2,
"is_parallel": true,
"self": 0.0004684270000439028
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1229.2781177449706,
"count": 231818,
"is_parallel": true,
"self": 37.79552321387291,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 76.90503935606296,
"count": 231818,
"is_parallel": true,
"self": 76.90503935606296
},
"communicator.exchange": {
"total": 1023.9719016030145,
"count": 231818,
"is_parallel": true,
"self": 1023.9719016030145
},
"steps_from_proto": {
"total": 90.60565357202012,
"count": 231818,
"is_parallel": true,
"self": 36.8241804618811,
"children": {
"_process_rank_one_or_two_observation": {
"total": 53.78147311013902,
"count": 463636,
"is_parallel": true,
"self": 53.78147311013902
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 506.4037560418889,
"count": 231819,
"self": 6.477804845913852,
"children": {
"process_trajectory": {
"total": 156.183052428974,
"count": 231819,
"self": 154.92291758897449,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2601348399995231,
"count": 10,
"self": 1.2601348399995231
}
}
},
"_update_policy": {
"total": 343.74289876700107,
"count": 97,
"self": 287.098767459999,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.644131307002056,
"count": 2910,
"self": 56.644131307002056
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1649999578366987e-06,
"count": 1,
"self": 1.1649999578366987e-06
},
"TrainerController._save_models": {
"total": 0.17906523700003163,
"count": 1,
"self": 0.003007151000019803,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17605808600001183,
"count": 1,
"self": 0.17605808600001183
}
}
}
}
}
}
}