ppo-Huggy / run_logs /timers.json
Larxel's picture
Huggy
5382299
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.405466914176941,
"min": 1.405466914176941,
"max": 1.425194501876831,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69937.4375,
"min": 67964.1328125,
"max": 77507.7734375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 96.0757281553398,
"min": 89.86,
"max": 398.96031746031747,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49479.0,
"min": 48994.0,
"max": 50269.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999927.0,
"min": 49968.0,
"max": 1999927.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999927.0,
"min": 49968.0,
"max": 1999927.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.444751739501953,
"min": 0.03524530306458473,
"max": 2.46439790725708,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1259.047119140625,
"min": 4.405663013458252,
"max": 1304.971923828125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.720055018119442,
"min": 1.7263272607326507,
"max": 3.8882071605095496,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1915.8283343315125,
"min": 215.79090759158134,
"max": 2021.517416536808,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.720055018119442,
"min": 1.7263272607326507,
"max": 3.8882071605095496,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1915.8283343315125,
"min": 215.79090759158134,
"max": 2021.517416536808,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015757425315193058,
"min": 0.013559923753200564,
"max": 0.019373413267506596,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04727227594557917,
"min": 0.02711984750640113,
"max": 0.056160044804467665,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05312056657340791,
"min": 0.02325841284667452,
"max": 0.05827323897845215,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15936169972022374,
"min": 0.04651682569334904,
"max": 0.17481971693535645,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4249488583833227e-06,
"min": 3.4249488583833227e-06,
"max": 0.00029534235155255007,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0274846575149968e-05,
"min": 1.0274846575149968e-05,
"max": 0.0008441347686217498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1011416166666667,
"min": 0.1011416166666667,
"max": 0.19844745000000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3034248500000001,
"min": 0.2074607,
"max": 0.58137825,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.696667166666652e-05,
"min": 6.696667166666652e-05,
"max": 0.004922527755000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020090001499999956,
"min": 0.00020090001499999956,
"max": 0.014070774675,
"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": "1680451632",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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 --resume",
"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": "1680454045"
},
"total": 2412.906536095,
"count": 1,
"self": 0.4368444659994566,
"children": {
"run_training.setup": {
"total": 0.18185419399992497,
"count": 1,
"self": 0.18185419399992497
},
"TrainerController.start_learning": {
"total": 2412.2878374350003,
"count": 1,
"self": 4.464983001039855,
"children": {
"TrainerController._reset_env": {
"total": 4.284028089000003,
"count": 1,
"self": 4.284028089000003
},
"TrainerController.advance": {
"total": 2403.40850354896,
"count": 231545,
"self": 4.718786814953546,
"children": {
"env_step": {
"total": 1901.2087196829962,
"count": 231545,
"self": 1609.976504623916,
"children": {
"SubprocessEnvManager._take_step": {
"total": 288.26125485406305,
"count": 231545,
"self": 17.18425062397182,
"children": {
"TorchPolicy.evaluate": {
"total": 271.07700423009123,
"count": 222943,
"self": 271.07700423009123
}
}
},
"workers": {
"total": 2.970960205017036,
"count": 231545,
"self": 0.0,
"children": {
"worker_root": {
"total": 2403.9026636239328,
"count": 231545,
"is_parallel": true,
"self": 1087.3338151668806,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0012492630000906502,
"count": 1,
"is_parallel": true,
"self": 0.0004094970001915499,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008397659998991003,
"count": 2,
"is_parallel": true,
"self": 0.0008397659998991003
}
}
},
"UnityEnvironment.step": {
"total": 0.030621792999909303,
"count": 1,
"is_parallel": true,
"self": 0.000273857999673055,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020130699999754142,
"count": 1,
"is_parallel": true,
"self": 0.00020130699999754142
},
"communicator.exchange": {
"total": 0.02930025800014846,
"count": 1,
"is_parallel": true,
"self": 0.02930025800014846
},
"steps_from_proto": {
"total": 0.0008463700000902463,
"count": 1,
"is_parallel": true,
"self": 0.00038065700005063263,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004657130000396137,
"count": 2,
"is_parallel": true,
"self": 0.0004657130000396137
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1316.5688484570521,
"count": 231544,
"is_parallel": true,
"self": 37.76732766512578,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.1043516779855,
"count": 231544,
"is_parallel": true,
"self": 85.1043516779855
},
"communicator.exchange": {
"total": 1101.5137283549532,
"count": 231544,
"is_parallel": true,
"self": 1101.5137283549532
},
"steps_from_proto": {
"total": 92.18344075898767,
"count": 231544,
"is_parallel": true,
"self": 37.142740356779086,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.040700402208586,
"count": 463088,
"is_parallel": true,
"self": 55.040700402208586
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 497.4809970510105,
"count": 231545,
"self": 6.712605059066391,
"children": {
"process_trajectory": {
"total": 134.67484454994496,
"count": 231545,
"self": 133.27194249494414,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4029020550008227,
"count": 10,
"self": 1.4029020550008227
}
}
},
"_update_policy": {
"total": 356.09354744199914,
"count": 97,
"self": 297.84366984601206,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.24987759598707,
"count": 2910,
"self": 58.24987759598707
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.929999578162096e-07,
"count": 1,
"self": 9.929999578162096e-07
},
"TrainerController._save_models": {
"total": 0.13032180300024265,
"count": 1,
"self": 0.0025567830002728442,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1277650199999698,
"count": 1,
"self": 0.1277650199999698
}
}
}
}
}
}
}