SnowballTarget / run_logs /timers.json
nokotin's picture
first model attempt
19b908f
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.1238728761672974,
"min": 1.1238728761672974,
"max": 2.8723747730255127,
"count": 15
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 11571.39453125,
"min": 11087.89453125,
"max": 29415.990234375,
"count": 15
},
"SnowballTarget.Step.mean": {
"value": 149984.0,
"min": 9952.0,
"max": 149984.0,
"count": 15
},
"SnowballTarget.Step.sum": {
"value": 149984.0,
"min": 9952.0,
"max": 149984.0,
"count": 15
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.105291366577148,
"min": 0.22913910448551178,
"max": 12.105291366577148,
"count": 15
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2481.584716796875,
"min": 44.45298767089844,
"max": 2481.584716796875,
"count": 15
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 15
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 15
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0701757237479529,
"min": 0.06335765878354911,
"max": 0.07411811662000128,
"count": 15
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3508786187397645,
"min": 0.25343063513419645,
"max": 0.3528973959744725,
"count": 15
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2231794206535115,
"min": 0.10514760009862265,
"max": 0.29542136170408306,
"count": 15
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.1158971032675575,
"min": 0.4205904003944906,
"max": 1.438370182525878,
"count": 15
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 9.776096741333334e-06,
"min": 9.776096741333334e-06,
"max": 0.000289176003608,
"count": 15
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 4.888048370666667e-05,
"min": 4.888048370666667e-05,
"max": 0.0013471360509546666,
"count": 15
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10325866666666668,
"min": 0.10325866666666668,
"max": 0.19639199999999998,
"count": 15
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5162933333333334,
"min": 0.43943466666666664,
"max": 0.9490453333333333,
"count": 15
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00017260746666666673,
"min": 0.00017260746666666673,
"max": 0.004819960799999999,
"count": 15
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0008630373333333337,
"min": 0.0008630373333333337,
"max": 0.022457362133333336,
"count": 15
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 24.10909090909091,
"min": 2.8636363636363638,
"max": 24.10909090909091,
"count": 15
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1326.0,
"min": 126.0,
"max": 1326.0,
"count": 15
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.10909090909091,
"min": 2.8636363636363638,
"max": 24.10909090909091,
"count": 15
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1326.0,
"min": 126.0,
"max": 1326.0,
"count": 15
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 15
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 15
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1691251181",
"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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"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": "1691251542"
},
"total": 360.529759833,
"count": 1,
"self": 0.79330493599997,
"children": {
"run_training.setup": {
"total": 0.04129737400000977,
"count": 1,
"self": 0.04129737400000977
},
"TrainerController.start_learning": {
"total": 359.69515752300003,
"count": 1,
"self": 0.47592709799801014,
"children": {
"TrainerController._reset_env": {
"total": 5.2158308470000065,
"count": 1,
"self": 5.2158308470000065
},
"TrainerController.advance": {
"total": 353.778098960002,
"count": 13689,
"self": 0.2163441989980015,
"children": {
"env_step": {
"total": 353.561754761004,
"count": 13689,
"self": 256.7123442550029,
"children": {
"SubprocessEnvManager._take_step": {
"total": 96.62455921899112,
"count": 13689,
"self": 1.4380496909927274,
"children": {
"TorchPolicy.evaluate": {
"total": 95.1865095279984,
"count": 13689,
"self": 95.1865095279984
}
}
},
"workers": {
"total": 0.22485128700998303,
"count": 13689,
"self": 0.0,
"children": {
"worker_root": {
"total": 358.3854390059983,
"count": 13689,
"is_parallel": true,
"self": 168.05099554399436,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0050706789999708235,
"count": 1,
"is_parallel": true,
"self": 0.0035147119999692222,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015559670000016013,
"count": 10,
"is_parallel": true,
"self": 0.0015559670000016013
}
}
},
"UnityEnvironment.step": {
"total": 0.035259419999988495,
"count": 1,
"is_parallel": true,
"self": 0.00046702800005959944,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003246339999805059,
"count": 1,
"is_parallel": true,
"self": 0.0003246339999805059
},
"communicator.exchange": {
"total": 0.032322187999966445,
"count": 1,
"is_parallel": true,
"self": 0.032322187999966445
},
"steps_from_proto": {
"total": 0.0021455699999819444,
"count": 1,
"is_parallel": true,
"self": 0.0004156149999516856,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017299550000302588,
"count": 10,
"is_parallel": true,
"self": 0.0017299550000302588
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 190.33444346200395,
"count": 13688,
"is_parallel": true,
"self": 8.064682854007458,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.0613595640033395,
"count": 13688,
"is_parallel": true,
"self": 4.0613595640033395
},
"communicator.exchange": {
"total": 150.88138836499695,
"count": 13688,
"is_parallel": true,
"self": 150.88138836499695
},
"steps_from_proto": {
"total": 27.327012678996198,
"count": 13688,
"is_parallel": true,
"self": 5.107588372005409,
"children": {
"_process_rank_one_or_two_observation": {
"total": 22.21942430699079,
"count": 136880,
"is_parallel": true,
"self": 22.21942430699079
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001758739999786485,
"count": 1,
"self": 0.0001758739999786485,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 351.0450216759495,
"count": 333395,
"is_parallel": true,
"self": 7.462730935964771,
"children": {
"process_trajectory": {
"total": 192.28488343498464,
"count": 333395,
"is_parallel": true,
"self": 190.77593825598467,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5089451789999657,
"count": 3,
"is_parallel": true,
"self": 1.5089451789999657
}
}
},
"_update_policy": {
"total": 151.2974073050001,
"count": 68,
"is_parallel": true,
"self": 56.949398558001974,
"children": {
"TorchPPOOptimizer.update": {
"total": 94.34800874699812,
"count": 3465,
"is_parallel": true,
"self": 94.34800874699812
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.22512474400002702,
"count": 1,
"self": 0.0010954410000749704,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22402930299995205,
"count": 1,
"self": 0.22402930299995205
}
}
}
}
}
}
}