GBjorn's picture
First Push
7c8c617
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7594660520553589,
"min": 0.7594660520553589,
"max": 2.8595330715179443,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7251.3818359375,
"min": 7251.3818359375,
"max": 29284.478515625,
"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": 12.94239330291748,
"min": 0.4285227060317993,
"max": 12.94239330291748,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2523.7666015625,
"min": 83.13340759277344,
"max": 2629.416015625,
"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": 0.06881204762821118,
"min": 0.06392693567311154,
"max": 0.0759288905973674,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2752481905128447,
"min": 0.2617220306819232,
"max": 0.379644452986837,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19457337041111553,
"min": 0.14478838008796502,
"max": 0.27896489108017847,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7782934816444621,
"min": 0.5791535203518601,
"max": 1.383941097294583,
"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": 25.34090909090909,
"min": 3.8181818181818183,
"max": 25.70909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1115.0,
"min": 168.0,
"max": 1414.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.34090909090909,
"min": 3.8181818181818183,
"max": 25.70909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1115.0,
"min": 168.0,
"max": 1414.0,
"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": "1701942259",
"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": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1701942796"
},
"total": 536.401177773,
"count": 1,
"self": 0.4312214929999527,
"children": {
"run_training.setup": {
"total": 0.061959989999991194,
"count": 1,
"self": 0.061959989999991194
},
"TrainerController.start_learning": {
"total": 535.90799629,
"count": 1,
"self": 0.6609538439961398,
"children": {
"TrainerController._reset_env": {
"total": 3.428414681999982,
"count": 1,
"self": 3.428414681999982
},
"TrainerController.advance": {
"total": 531.720991950004,
"count": 18200,
"self": 0.33977476300083254,
"children": {
"env_step": {
"total": 531.3812171870031,
"count": 18200,
"self": 362.2667570369952,
"children": {
"SubprocessEnvManager._take_step": {
"total": 168.6182722270002,
"count": 18200,
"self": 1.6696851299903415,
"children": {
"TorchPolicy.evaluate": {
"total": 166.94858709700986,
"count": 18200,
"self": 166.94858709700986
}
}
},
"workers": {
"total": 0.4961879230077102,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 534.3084236770047,
"count": 18200,
"is_parallel": true,
"self": 259.48784191400836,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0052718329999947855,
"count": 1,
"is_parallel": true,
"self": 0.0036843369999814968,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015874960000132887,
"count": 10,
"is_parallel": true,
"self": 0.0015874960000132887
}
}
},
"UnityEnvironment.step": {
"total": 0.0381794030000151,
"count": 1,
"is_parallel": true,
"self": 0.0006683830000611124,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046985800003085387,
"count": 1,
"is_parallel": true,
"self": 0.00046985800003085387
},
"communicator.exchange": {
"total": 0.034782653999968716,
"count": 1,
"is_parallel": true,
"self": 0.034782653999968716
},
"steps_from_proto": {
"total": 0.0022585079999544178,
"count": 1,
"is_parallel": true,
"self": 0.0004387239999346093,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018197840000198084,
"count": 10,
"is_parallel": true,
"self": 0.0018197840000198084
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 274.82058176299637,
"count": 18199,
"is_parallel": true,
"self": 11.845600509009671,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.179283120993489,
"count": 18199,
"is_parallel": true,
"self": 6.179283120993489
},
"communicator.exchange": {
"total": 216.91583567100025,
"count": 18199,
"is_parallel": true,
"self": 216.91583567100025
},
"steps_from_proto": {
"total": 39.87986246199296,
"count": 18199,
"is_parallel": true,
"self": 7.552424652976356,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.3274378090166,
"count": 181990,
"is_parallel": true,
"self": 32.3274378090166
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.0390999970441044e-05,
"count": 1,
"self": 4.0390999970441044e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 526.879875048977,
"count": 567467,
"is_parallel": true,
"self": 12.788911007947718,
"children": {
"process_trajectory": {
"total": 297.2383380870294,
"count": 567467,
"is_parallel": true,
"self": 296.68405195102935,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5542861360000302,
"count": 4,
"is_parallel": true,
"self": 0.5542861360000302
}
}
},
"_update_policy": {
"total": 216.85262595399996,
"count": 90,
"is_parallel": true,
"self": 70.74599822499948,
"children": {
"TorchPPOOptimizer.update": {
"total": 146.10662772900048,
"count": 4587,
"is_parallel": true,
"self": 146.10662772900048
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09759542299991608,
"count": 1,
"self": 0.0008788639999011139,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09671655900001497,
"count": 1,
"self": 0.09671655900001497
}
}
}
}
}
}
}