ppo-SnowbalTarget / run_logs /timers.json
jjturner270's picture
Initial Commit
67e4fe5 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.1438989639282227,
"min": 1.1438989639282227,
"max": 2.8750736713409424,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10947.11328125,
"min": 10947.11328125,
"max": 29506.880859375,
"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": 12.3394193649292,
"min": 0.3109203279018402,
"max": 12.3394193649292,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2406.186767578125,
"min": 60.31854248046875,
"max": 2477.65087890625,
"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": 0.0638223718315381,
"min": 0.061741177060792005,
"max": 0.07340799011063948,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2552894873261524,
"min": 0.2552894873261524,
"max": 0.3591045995719968,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2258545412298511,
"min": 0.09282792331513894,
"max": 0.2721436358257836,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9034181649194044,
"min": 0.37131169326055574,
"max": 1.2949003156493692,
"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": 24.59090909090909,
"min": 2.840909090909091,
"max": 24.59090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1082.0,
"min": 125.0,
"max": 1336.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.59090909090909,
"min": 2.840909090909091,
"max": 24.59090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1082.0,
"min": 125.0,
"max": 1336.0,
"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": "1744327084",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/ubuntu/miniconda3/envs/mltrain2/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1744327658"
},
"total": 574.077305969,
"count": 1,
"self": 0.3731068139995841,
"children": {
"run_training.setup": {
"total": 0.019284339000478212,
"count": 1,
"self": 0.019284339000478212
},
"TrainerController.start_learning": {
"total": 573.684914816,
"count": 1,
"self": 0.33176658397587744,
"children": {
"TrainerController._reset_env": {
"total": 1.3910847480001394,
"count": 1,
"self": 1.3910847480001394
},
"TrainerController.advance": {
"total": 571.9117993190239,
"count": 18205,
"self": 0.16282037016935647,
"children": {
"env_step": {
"total": 571.7489789488545,
"count": 18205,
"self": 510.7330667797023,
"children": {
"SubprocessEnvManager._take_step": {
"total": 60.86264999611467,
"count": 18205,
"self": 0.9124921591001112,
"children": {
"TorchPolicy.evaluate": {
"total": 59.95015783701456,
"count": 18205,
"self": 59.95015783701456
}
}
},
"workers": {
"total": 0.15326217303754675,
"count": 18205,
"self": 0.0,
"children": {
"worker_root": {
"total": 572.4240925590093,
"count": 18205,
"is_parallel": true,
"self": 137.76795084703372,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018332569998165127,
"count": 1,
"is_parallel": true,
"self": 0.0006149959990580101,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012182610007585026,
"count": 10,
"is_parallel": true,
"self": 0.0012182610007585026
}
}
},
"UnityEnvironment.step": {
"total": 0.046618239999588695,
"count": 1,
"is_parallel": true,
"self": 0.0003422309991947259,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0006818179999754648,
"count": 1,
"is_parallel": true,
"self": 0.0006818179999754648
},
"communicator.exchange": {
"total": 0.04452579999997397,
"count": 1,
"is_parallel": true,
"self": 0.04452579999997397
},
"steps_from_proto": {
"total": 0.0010683910004445352,
"count": 1,
"is_parallel": true,
"self": 0.00020786800178029807,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008605229986642371,
"count": 10,
"is_parallel": true,
"self": 0.0008605229986642371
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 434.6561417119756,
"count": 18204,
"is_parallel": true,
"self": 15.24701050501244,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.428618981980435,
"count": 18204,
"is_parallel": true,
"self": 8.428618981980435
},
"communicator.exchange": {
"total": 363.477645594975,
"count": 18204,
"is_parallel": true,
"self": 363.477645594975
},
"steps_from_proto": {
"total": 47.5028666300077,
"count": 18204,
"is_parallel": true,
"self": 9.201226723889704,
"children": {
"_process_rank_one_or_two_observation": {
"total": 38.301639906118,
"count": 182040,
"is_parallel": true,
"self": 38.301639906118
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.210799998982111e-05,
"count": 1,
"self": 9.210799998982111e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 570.8921332188156,
"count": 327710,
"is_parallel": true,
"self": 3.1844177916855188,
"children": {
"process_trajectory": {
"total": 355.956552868126,
"count": 327710,
"is_parallel": true,
"self": 355.38912583312595,
"children": {
"RLTrainer._checkpoint": {
"total": 0.567427035000037,
"count": 4,
"is_parallel": true,
"self": 0.567427035000037
}
}
},
"_update_policy": {
"total": 211.75116255900411,
"count": 90,
"is_parallel": true,
"self": 26.311613466984454,
"children": {
"TorchPPOOptimizer.update": {
"total": 185.43954909201966,
"count": 4587,
"is_parallel": true,
"self": 185.43954909201966
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.05017205700005434,
"count": 1,
"self": 0.0006324270007098676,
"children": {
"RLTrainer._checkpoint": {
"total": 0.04953962999934447,
"count": 1,
"self": 0.04953962999934447
}
}
}
}
}
}
}