LemonIsGoose's picture
First Push
50697d7 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.374580442905426,
"min": 0.3643650412559509,
"max": 0.7337501645088196,
"count": 80
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 3560.012451171875,
"min": 3529.580078125,
"max": 7490.12158203125,
"count": 80
},
"SnowballTarget.Step.mean": {
"value": 999992.0,
"min": 209936.0,
"max": 999992.0,
"count": 80
},
"SnowballTarget.Step.sum": {
"value": 999992.0,
"min": 209936.0,
"max": 999992.0,
"count": 80
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.95432186126709,
"min": 11.86744213104248,
"max": 13.021476745605469,
"count": 80
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2526.0927734375,
"min": 2292.9599609375,
"max": 2656.4658203125,
"count": 80
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0724045507462613,
"min": 0.05778585477131784,
"max": 0.07941376969193145,
"count": 80
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2896182029850452,
"min": 0.23114341908527136,
"max": 0.3843103292450656,
"count": 80
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.14879775901927667,
"min": 0.13513713610522887,
"max": 0.20789627343708394,
"count": 80
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.5951910360771067,
"min": 0.5439493631323179,
"max": 1.0064598821541844,
"count": 80
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.402899532400004e-06,
"min": 1.402899532400004e-06,
"max": 0.0002383428205524,
"count": 80
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.611598129600016e-06,
"min": 5.611598129600016e-06,
"max": 0.001176864107712,
"count": 80
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.1004676,
"min": 0.1004676,
"max": 0.1794476,
"count": 80
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.4018704,
"min": 0.4018704,
"max": 0.892288,
"count": 80
},
"SnowballTarget.Policy.Beta.mean": {
"value": 3.3333240000000065e-05,
"min": 3.3333240000000065e-05,
"max": 0.00397443524,
"count": 80
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00013333296000000026,
"min": 0.00013333296000000026,
"max": 0.0196251712,
"count": 80
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 80
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 80
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.386363636363637,
"min": 23.0,
"max": 25.522727272727273,
"count": 80
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1117.0,
"min": 1020.0,
"max": 1400.0,
"count": 80
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.386363636363637,
"min": 23.0,
"max": 25.522727272727273,
"count": 80
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1117.0,
"min": 1020.0,
"max": 1400.0,
"count": 80
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 80
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 80
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1761814723",
"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 --resume",
"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": "1761816522"
},
"total": 1799.3915474189998,
"count": 1,
"self": 0.7804227439996794,
"children": {
"run_training.setup": {
"total": 0.0249263420000716,
"count": 1,
"self": 0.0249263420000716
},
"TrainerController.start_learning": {
"total": 1798.586198333,
"count": 1,
"self": 1.506672090992197,
"children": {
"TrainerController._reset_env": {
"total": 1.917800995000107,
"count": 1,
"self": 1.917800995000107
},
"TrainerController.advance": {
"total": 1795.0394984730078,
"count": 72728,
"self": 1.4946366171966474,
"children": {
"env_step": {
"total": 1311.3305661559857,
"count": 72728,
"self": 1027.8489127318721,
"children": {
"SubprocessEnvManager._take_step": {
"total": 282.5614591920603,
"count": 72728,
"self": 5.177399152053113,
"children": {
"TorchPolicy.evaluate": {
"total": 277.38406004000717,
"count": 72728,
"self": 277.38406004000717
}
}
},
"workers": {
"total": 0.9201942320532908,
"count": 72728,
"self": 0.0,
"children": {
"worker_root": {
"total": 1792.333856837914,
"count": 72728,
"is_parallel": true,
"self": 887.5131611378256,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002112542000304529,
"count": 1,
"is_parallel": true,
"self": 0.0006674189999102964,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014451230003942328,
"count": 10,
"is_parallel": true,
"self": 0.0014451230003942328
}
}
},
"UnityEnvironment.step": {
"total": 0.036311199000010674,
"count": 1,
"is_parallel": true,
"self": 0.0005774600008408015,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047467899958064663,
"count": 1,
"is_parallel": true,
"self": 0.00047467899958064663
},
"communicator.exchange": {
"total": 0.03347014599967224,
"count": 1,
"is_parallel": true,
"self": 0.03347014599967224
},
"steps_from_proto": {
"total": 0.0017889139999169856,
"count": 1,
"is_parallel": true,
"self": 0.0003405359998396307,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001448378000077355,
"count": 10,
"is_parallel": true,
"self": 0.001448378000077355
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 904.8206957000884,
"count": 72727,
"is_parallel": true,
"self": 41.832635985086654,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.16762553002809,
"count": 72727,
"is_parallel": true,
"self": 23.16762553002809
},
"communicator.exchange": {
"total": 688.5721447390097,
"count": 72727,
"is_parallel": true,
"self": 688.5721447390097
},
"steps_from_proto": {
"total": 151.24828944596402,
"count": 72727,
"is_parallel": true,
"self": 27.119742071854034,
"children": {
"_process_rank_one_or_two_observation": {
"total": 124.12854737410998,
"count": 727270,
"is_parallel": true,
"self": 124.12854737410998
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 482.21429569982547,
"count": 72728,
"self": 1.873519834840863,
"children": {
"process_trajectory": {
"total": 105.22609955198868,
"count": 72728,
"self": 103.67849293198788,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5476066200008063,
"count": 16,
"self": 1.5476066200008063
}
}
},
"_update_policy": {
"total": 375.1146763129959,
"count": 363,
"self": 152.87356081701228,
"children": {
"TorchPPOOptimizer.update": {
"total": 222.24111549598365,
"count": 18510,
"self": 222.24111549598365
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1219999578315765e-06,
"count": 1,
"self": 1.1219999578315765e-06
},
"TrainerController._save_models": {
"total": 0.12222565199999735,
"count": 1,
"self": 0.001639331000205857,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1205863209997915,
"count": 1,
"self": 0.1205863209997915
}
}
}
}
}
}
}