ppo-Huggy / run_logs /timers.json
lambdavi's picture
Huggy
f79d0d6
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.408495545387268,
"min": 1.408495545387268,
"max": 1.4300010204315186,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70250.125,
"min": 67565.2421875,
"max": 78901.390625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 79.23987034035656,
"min": 72.00875912408759,
"max": 402.616,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 48891.0,
"min": 48764.0,
"max": 50327.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999973.0,
"min": 49886.0,
"max": 1999973.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999973.0,
"min": 49886.0,
"max": 1999973.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.447506904602051,
"min": 0.05929029360413551,
"max": 2.5781219005584717,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1510.11181640625,
"min": 7.351996421813965,
"max": 1693.54345703125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.735927064279683,
"min": 1.7976336584937187,
"max": 4.0541660182119355,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2305.0669986605644,
"min": 222.90657365322113,
"max": 2712.536199450493,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.735927064279683,
"min": 1.7976336584937187,
"max": 4.0541660182119355,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2305.0669986605644,
"min": 222.90657365322113,
"max": 2712.536199450493,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017717409052420408,
"min": 0.013689214720337378,
"max": 0.020197423046435386,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05315222715726123,
"min": 0.027378429440674756,
"max": 0.057170435370062486,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05410215146839619,
"min": 0.0239123269294699,
"max": 0.05930826061715683,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16230645440518857,
"min": 0.0478246538589398,
"max": 0.17485884005824726,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.899998700033334e-06,
"min": 3.899998700033334e-06,
"max": 0.00029527905157365,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1699996100100001e-05,
"min": 1.1699996100100001e-05,
"max": 0.0008439120186959999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10129996666666669,
"min": 0.10129996666666669,
"max": 0.19842634999999995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30389990000000006,
"min": 0.20773055,
"max": 0.5813039999999998,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.48683366666667e-05,
"min": 7.48683366666667e-05,
"max": 0.004921474864999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002246050100000001,
"min": 0.0002246050100000001,
"max": 0.0140670696,
"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": "1701033181",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1701035645"
},
"total": 2464.181992527,
"count": 1,
"self": 0.4479727780003486,
"children": {
"run_training.setup": {
"total": 0.055302016000041476,
"count": 1,
"self": 0.055302016000041476
},
"TrainerController.start_learning": {
"total": 2463.6787177329998,
"count": 1,
"self": 4.397604940101246,
"children": {
"TrainerController._reset_env": {
"total": 3.5569821279999587,
"count": 1,
"self": 3.5569821279999587
},
"TrainerController.advance": {
"total": 2455.625687445898,
"count": 233530,
"self": 4.710790184116831,
"children": {
"env_step": {
"total": 1922.5126863709238,
"count": 233530,
"self": 1585.3966426431007,
"children": {
"SubprocessEnvManager._take_step": {
"total": 334.2173321149754,
"count": 233530,
"self": 16.792074962998527,
"children": {
"TorchPolicy.evaluate": {
"total": 317.4252571519769,
"count": 223005,
"self": 317.4252571519769
}
}
},
"workers": {
"total": 2.898711612847819,
"count": 233530,
"self": 0.0,
"children": {
"worker_root": {
"total": 2456.0543881460685,
"count": 233530,
"is_parallel": true,
"self": 1175.5724229739567,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008608750000576038,
"count": 1,
"is_parallel": true,
"self": 0.00021961700008432672,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000641257999973277,
"count": 2,
"is_parallel": true,
"self": 0.000641257999973277
}
}
},
"UnityEnvironment.step": {
"total": 0.03161054100007732,
"count": 1,
"is_parallel": true,
"self": 0.0003043200001684454,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002024550000214731,
"count": 1,
"is_parallel": true,
"self": 0.0002024550000214731
},
"communicator.exchange": {
"total": 0.03038330199990469,
"count": 1,
"is_parallel": true,
"self": 0.03038330199990469
},
"steps_from_proto": {
"total": 0.0007204639999827123,
"count": 1,
"is_parallel": true,
"self": 0.00019650100000490056,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005239629999778117,
"count": 2,
"is_parallel": true,
"self": 0.0005239629999778117
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1280.4819651721118,
"count": 233529,
"is_parallel": true,
"self": 39.63026586016531,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.97218221201206,
"count": 233529,
"is_parallel": true,
"self": 80.97218221201206
},
"communicator.exchange": {
"total": 1071.6298001279706,
"count": 233529,
"is_parallel": true,
"self": 1071.6298001279706
},
"steps_from_proto": {
"total": 88.24971697196395,
"count": 233529,
"is_parallel": true,
"self": 30.81951608112263,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.43020089084132,
"count": 467058,
"is_parallel": true,
"self": 57.43020089084132
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 528.4022108908576,
"count": 233530,
"self": 6.807577750967198,
"children": {
"process_trajectory": {
"total": 163.93876769589247,
"count": 233530,
"self": 162.88427311589305,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0544945799994139,
"count": 10,
"self": 1.0544945799994139
}
}
},
"_update_policy": {
"total": 357.655865443998,
"count": 97,
"self": 293.44406693500093,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.21179850899705,
"count": 2910,
"self": 64.21179850899705
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.330001375928987e-07,
"count": 1,
"self": 9.330001375928987e-07
},
"TrainerController._save_models": {
"total": 0.09844228600013594,
"count": 1,
"self": 0.0016561719999117486,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09678611400022419,
"count": 1,
"self": 0.09678611400022419
}
}
}
}
}
}
}