rwr20's picture
First Push
821b354 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0253276824951172,
"min": 1.0253276824951172,
"max": 2.8511836528778076,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9789.8291015625,
"min": 9789.8291015625,
"max": 29230.3359375,
"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": 12.641348838806152,
"min": 0.3219224512577057,
"max": 12.641348838806152,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2465.06298828125,
"min": 62.45295333862305,
"max": 2575.12939453125,
"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": 0.06541694653433118,
"min": 0.0595636931932609,
"max": 0.07928308617898866,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2616677861373247,
"min": 0.24892791075056747,
"max": 0.3552745606832426,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21186259192387188,
"min": 0.14937025082626326,
"max": 0.2692673066667482,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8474503676954875,
"min": 0.597481003305053,
"max": 1.346336533333741,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.130097290000004e-06,
"min": 8.130097290000004e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.2520389160000015e-05,
"min": 3.2520389160000015e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10271,
"min": 0.10271,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41084,
"min": 0.41084,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00014522900000000006,
"min": 0.00014522900000000006,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005809160000000002,
"min": 0.0005809160000000002,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 24.772727272727273,
"min": 4.045454545454546,
"max": 25.318181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1090.0,
"min": 178.0,
"max": 1367.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.772727272727273,
"min": 4.045454545454546,
"max": 25.318181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1090.0,
"min": 178.0,
"max": 1367.0,
"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": "1714812168",
"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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714812619"
},
"total": 450.834340267,
"count": 1,
"self": 0.4391323800000464,
"children": {
"run_training.setup": {
"total": 0.0627717060001487,
"count": 1,
"self": 0.0627717060001487
},
"TrainerController.start_learning": {
"total": 450.3324361809998,
"count": 1,
"self": 0.5568509820013787,
"children": {
"TrainerController._reset_env": {
"total": 3.044895593000092,
"count": 1,
"self": 3.044895593000092
},
"TrainerController.advance": {
"total": 446.6360054039985,
"count": 18200,
"self": 0.26553876098205365,
"children": {
"env_step": {
"total": 446.37046664301647,
"count": 18200,
"self": 290.6709277390157,
"children": {
"SubprocessEnvManager._take_step": {
"total": 155.42312143500567,
"count": 18200,
"self": 1.455153224010246,
"children": {
"TorchPolicy.evaluate": {
"total": 153.96796821099542,
"count": 18200,
"self": 153.96796821099542
}
}
},
"workers": {
"total": 0.2764174689950778,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 449.15598259100534,
"count": 18200,
"is_parallel": true,
"self": 224.8919560620168,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008054547000028833,
"count": 1,
"is_parallel": true,
"self": 0.0038505489999351994,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004203998000093634,
"count": 10,
"is_parallel": true,
"self": 0.004203998000093634
}
}
},
"UnityEnvironment.step": {
"total": 0.039368650000142225,
"count": 1,
"is_parallel": true,
"self": 0.0007385230003364995,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004068830000960588,
"count": 1,
"is_parallel": true,
"self": 0.0004068830000960588
},
"communicator.exchange": {
"total": 0.03594008099980783,
"count": 1,
"is_parallel": true,
"self": 0.03594008099980783
},
"steps_from_proto": {
"total": 0.0022831629999018332,
"count": 1,
"is_parallel": true,
"self": 0.000454530999832059,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018286320000697742,
"count": 10,
"is_parallel": true,
"self": 0.0018286320000697742
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 224.26402652898855,
"count": 18199,
"is_parallel": true,
"self": 10.332756390950408,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.370719444013957,
"count": 18199,
"is_parallel": true,
"self": 5.370719444013957
},
"communicator.exchange": {
"total": 174.8374517279974,
"count": 18199,
"is_parallel": true,
"self": 174.8374517279974
},
"steps_from_proto": {
"total": 33.72309896602678,
"count": 18199,
"is_parallel": true,
"self": 6.357074519028174,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.36602444699861,
"count": 181990,
"is_parallel": true,
"self": 27.36602444699861
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011537299997144146,
"count": 1,
"self": 0.00011537299997144146,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 441.1893991550048,
"count": 680995,
"is_parallel": true,
"self": 14.204714947065213,
"children": {
"process_trajectory": {
"total": 241.6702348799388,
"count": 680995,
"is_parallel": true,
"self": 241.054008206939,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6162266729998009,
"count": 4,
"is_parallel": true,
"self": 0.6162266729998009
}
}
},
"_update_policy": {
"total": 185.31444932800082,
"count": 90,
"is_parallel": true,
"self": 56.224243879994674,
"children": {
"TorchPPOOptimizer.update": {
"total": 129.09020544800615,
"count": 4584,
"is_parallel": true,
"self": 129.09020544800615
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.0945688289998543,
"count": 1,
"self": 0.0009893689998534683,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09357946000000084,
"count": 1,
"self": 0.09357946000000084
}
}
}
}
}
}
}