boruyang's picture
First Push
9f5e952 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8978010416030884,
"min": 0.8966231346130371,
"max": 2.868410110473633,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8572.2041015625,
"min": 8572.2041015625,
"max": 29343.8359375,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.031074523925781,
"min": 0.478193998336792,
"max": 13.031074523925781,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2541.0595703125,
"min": 92.76963806152344,
"max": 2621.9169921875,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0706703049477701,
"min": 0.05835007386072082,
"max": 0.07387338245233895,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2826812197910804,
"min": 0.2334002954428833,
"max": 0.36935633644701316,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21970037626577357,
"min": 0.12919206884872242,
"max": 0.2767119737816792,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8788015050630943,
"min": 0.5167682753948897,
"max": 1.3125232764903236,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.772727272727273,
"min": 3.4318181818181817,
"max": 25.963636363636365,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1134.0,
"min": 151.0,
"max": 1428.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.772727272727273,
"min": 3.4318181818181817,
"max": 25.963636363636365,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1134.0,
"min": 151.0,
"max": 1428.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1706936244",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1706936831"
},
"total": 587.0360296639999,
"count": 1,
"self": 0.5414878369997496,
"children": {
"run_training.setup": {
"total": 0.06596581400003743,
"count": 1,
"self": 0.06596581400003743
},
"TrainerController.start_learning": {
"total": 586.4285760130001,
"count": 1,
"self": 0.792302606001158,
"children": {
"TrainerController._reset_env": {
"total": 4.418071330999965,
"count": 1,
"self": 4.418071330999965
},
"TrainerController.advance": {
"total": 581.108100601999,
"count": 18199,
"self": 0.422713171981286,
"children": {
"env_step": {
"total": 580.6853874300177,
"count": 18199,
"self": 380.855732039033,
"children": {
"SubprocessEnvManager._take_step": {
"total": 199.42798979200575,
"count": 18199,
"self": 2.340706883039047,
"children": {
"TorchPolicy.evaluate": {
"total": 197.0872829089667,
"count": 18199,
"self": 197.0872829089667
}
}
},
"workers": {
"total": 0.4016655989789797,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 584.5987454109907,
"count": 18199,
"is_parallel": true,
"self": 283.74692972299704,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00822287599999072,
"count": 1,
"is_parallel": true,
"self": 0.004942186999869591,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0032806890001211286,
"count": 10,
"is_parallel": true,
"self": 0.0032806890001211286
}
}
},
"UnityEnvironment.step": {
"total": 0.04335899099987728,
"count": 1,
"is_parallel": true,
"self": 0.0007571900002858456,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046065099991210445,
"count": 1,
"is_parallel": true,
"self": 0.00046065099991210445
},
"communicator.exchange": {
"total": 0.039862539999830915,
"count": 1,
"is_parallel": true,
"self": 0.039862539999830915
},
"steps_from_proto": {
"total": 0.0022786099998484133,
"count": 1,
"is_parallel": true,
"self": 0.0004509670002335042,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001827642999614909,
"count": 10,
"is_parallel": true,
"self": 0.001827642999614909
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 300.8518156879936,
"count": 18198,
"is_parallel": true,
"self": 14.757832525000367,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.214779939989285,
"count": 18198,
"is_parallel": true,
"self": 7.214779939989285
},
"communicator.exchange": {
"total": 235.83768679699438,
"count": 18198,
"is_parallel": true,
"self": 235.83768679699438
},
"steps_from_proto": {
"total": 43.04151642600959,
"count": 18198,
"is_parallel": true,
"self": 8.347410323010536,
"children": {
"_process_rank_one_or_two_observation": {
"total": 34.69410610299906,
"count": 181980,
"is_parallel": true,
"self": 34.69410610299906
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015215500002341287,
"count": 1,
"self": 0.00015215500002341287,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 572.9854198090231,
"count": 913419,
"is_parallel": true,
"self": 20.746561453039703,
"children": {
"process_trajectory": {
"total": 322.6011442999834,
"count": 913419,
"is_parallel": true,
"self": 322.0280722109833,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5730720890001066,
"count": 4,
"is_parallel": true,
"self": 0.5730720890001066
}
}
},
"_update_policy": {
"total": 229.63771405600005,
"count": 90,
"is_parallel": true,
"self": 60.33136058600917,
"children": {
"TorchPPOOptimizer.update": {
"total": 169.30635346999088,
"count": 4587,
"is_parallel": true,
"self": 169.30635346999088
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10994931899995208,
"count": 1,
"self": 0.0012126459998853534,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10873667300006673,
"count": 1,
"self": 0.10873667300006673
}
}
}
}
}
}
}