ZuzEL's picture
First Push
6e333c3 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.4230369031429291,
"min": 0.4190695285797119,
"max": 2.8659555912017822,
"count": 40
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 4318.36083984375,
"min": 4019.71484375,
"max": 29255.673828125,
"count": 40
},
"SnowballTarget.Step.mean": {
"value": 399992.0,
"min": 9952.0,
"max": 399992.0,
"count": 40
},
"SnowballTarget.Step.sum": {
"value": 399992.0,
"min": 9952.0,
"max": 399992.0,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.328252792358398,
"min": 0.3663052022457123,
"max": 13.404317855834961,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2599.00927734375,
"min": 71.0632095336914,
"max": 2747.88525390625,
"count": 40
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06839161595124489,
"min": 0.05863342262549778,
"max": 0.07830258064909595,
"count": 40
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27356646380497956,
"min": 0.23453369050199113,
"max": 0.366125584905853,
"count": 40
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18655752427145544,
"min": 0.10981202562335038,
"max": 0.2647619646992169,
"count": 40
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7462300970858218,
"min": 0.4392481024934015,
"max": 1.322167965419152,
"count": 40
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.891098702999994e-06,
"min": 3.891098702999994e-06,
"max": 0.000295941001353,
"count": 40
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.5564394811999976e-05,
"min": 1.5564394811999976e-05,
"max": 0.0014425800191399996,
"count": 40
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.101297,
"min": 0.101297,
"max": 0.19864700000000002,
"count": 40
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.405188,
"min": 0.405188,
"max": 0.98086,
"count": 40
},
"SnowballTarget.Policy.Beta.mean": {
"value": 7.472029999999992e-05,
"min": 7.472029999999992e-05,
"max": 0.004932485299999999,
"count": 40
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00029888119999999966,
"min": 0.00029888119999999966,
"max": 0.024044914,
"count": 40
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 40
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 40
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.681818181818183,
"min": 2.977272727272727,
"max": 26.618181818181817,
"count": 40
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1130.0,
"min": 131.0,
"max": 1464.0,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.681818181818183,
"min": 2.977272727272727,
"max": 26.618181818181817,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1130.0,
"min": 131.0,
"max": 1464.0,
"count": 40
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1779276247",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1779277192"
},
"total": 944.4329234209999,
"count": 1,
"self": 0.48037057999954413,
"children": {
"run_training.setup": {
"total": 0.025585541000509693,
"count": 1,
"self": 0.025585541000509693
},
"TrainerController.start_learning": {
"total": 943.9269672999999,
"count": 1,
"self": 0.7769151439888446,
"children": {
"TrainerController._reset_env": {
"total": 2.119051824000053,
"count": 1,
"self": 2.119051824000053
},
"TrainerController.advance": {
"total": 940.9482408250115,
"count": 36392,
"self": 0.8220438249527433,
"children": {
"env_step": {
"total": 688.3317350119814,
"count": 36392,
"self": 539.2395040629408,
"children": {
"SubprocessEnvManager._take_step": {
"total": 148.6458934690263,
"count": 36392,
"self": 2.6984049660641176,
"children": {
"TorchPolicy.evaluate": {
"total": 145.9474885029622,
"count": 36392,
"self": 145.9474885029622
}
}
},
"workers": {
"total": 0.4463374800143356,
"count": 36392,
"self": 0.0,
"children": {
"worker_root": {
"total": 940.5006694459962,
"count": 36392,
"is_parallel": true,
"self": 465.90896556810094,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001973123000425403,
"count": 1,
"is_parallel": true,
"self": 0.0005944359982095193,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013786870022158837,
"count": 10,
"is_parallel": true,
"self": 0.0013786870022158837
}
}
},
"UnityEnvironment.step": {
"total": 0.03704507100064802,
"count": 1,
"is_parallel": true,
"self": 0.0007199819992820267,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042335000034654513,
"count": 1,
"is_parallel": true,
"self": 0.00042335000034654513
},
"communicator.exchange": {
"total": 0.03382141300062358,
"count": 1,
"is_parallel": true,
"self": 0.03382141300062358
},
"steps_from_proto": {
"total": 0.0020803260003958712,
"count": 1,
"is_parallel": true,
"self": 0.00037994300055288477,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017003829998429865,
"count": 10,
"is_parallel": true,
"self": 0.0017003829998429865
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 474.59170387789527,
"count": 36391,
"is_parallel": true,
"self": 21.61946037173675,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 11.415324604967282,
"count": 36391,
"is_parallel": true,
"self": 11.415324604967282
},
"communicator.exchange": {
"total": 363.8498690350825,
"count": 36391,
"is_parallel": true,
"self": 363.8498690350825
},
"steps_from_proto": {
"total": 77.70704986610872,
"count": 36391,
"is_parallel": true,
"self": 13.893564590902315,
"children": {
"_process_rank_one_or_two_observation": {
"total": 63.8134852752064,
"count": 363910,
"is_parallel": true,
"self": 63.8134852752064
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 251.79446198807727,
"count": 36392,
"self": 0.892620320199967,
"children": {
"process_trajectory": {
"total": 56.1051556348757,
"count": 36392,
"self": 55.283395595874026,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8217600390016742,
"count": 8,
"self": 0.8217600390016742
}
}
},
"_update_policy": {
"total": 194.7966860330016,
"count": 181,
"self": 79.69765282798289,
"children": {
"TorchPPOOptimizer.update": {
"total": 115.09903320501871,
"count": 9228,
"self": 115.09903320501871
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0439998732181266e-06,
"count": 1,
"self": 1.0439998732181266e-06
},
"TrainerController._save_models": {
"total": 0.0827584629996636,
"count": 1,
"self": 0.0007983039995451691,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08196015900011844,
"count": 1,
"self": 0.08196015900011844
}
}
}
}
}
}
}