bramsikkens's picture
First Push
f951db8 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7607671022415161,
"min": 0.7607671022415161,
"max": 2.8752849102020264,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7272.1728515625,
"min": 7272.1728515625,
"max": 29477.421875,
"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": 12.925089836120605,
"min": 0.400587260723114,
"max": 12.925089836120605,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2520.392578125,
"min": 77.71392822265625,
"max": 2617.804931640625,
"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": 0.0686251861633911,
"min": 0.06271589000209453,
"max": 0.0757362710421576,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2745007446535644,
"min": 0.2542313728983715,
"max": 0.37868135521078805,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20981135705084192,
"min": 0.11954398132751093,
"max": 0.2791604054909126,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8392454282033677,
"min": 0.4781759253100437,
"max": 1.395802027454563,
"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": 25.477272727272727,
"min": 3.340909090909091,
"max": 25.477272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1121.0,
"min": 147.0,
"max": 1382.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.477272727272727,
"min": 3.340909090909091,
"max": 25.477272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1121.0,
"min": 147.0,
"max": 1382.0,
"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": "1706456274",
"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": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1706456778"
},
"total": 503.8905346299998,
"count": 1,
"self": 0.511558210999965,
"children": {
"run_training.setup": {
"total": 0.056273278999924514,
"count": 1,
"self": 0.056273278999924514
},
"TrainerController.start_learning": {
"total": 503.32270313999993,
"count": 1,
"self": 0.6343323129617602,
"children": {
"TrainerController._reset_env": {
"total": 3.115457498000069,
"count": 1,
"self": 3.115457498000069
},
"TrainerController.advance": {
"total": 499.4778702240385,
"count": 18200,
"self": 0.3262544110430099,
"children": {
"env_step": {
"total": 499.1516158129955,
"count": 18200,
"self": 328.604332442992,
"children": {
"SubprocessEnvManager._take_step": {
"total": 170.22727816103134,
"count": 18200,
"self": 1.6601878350093102,
"children": {
"TorchPolicy.evaluate": {
"total": 168.56709032602203,
"count": 18200,
"self": 168.56709032602203
}
}
},
"workers": {
"total": 0.3200052089721339,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 501.83413079901084,
"count": 18200,
"is_parallel": true,
"self": 247.5428047529806,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004322533000049589,
"count": 1,
"is_parallel": true,
"self": 0.0028482960001383617,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001474236999911227,
"count": 10,
"is_parallel": true,
"self": 0.001474236999911227
}
}
},
"UnityEnvironment.step": {
"total": 0.09181627799989656,
"count": 1,
"is_parallel": true,
"self": 0.0006990879999193567,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004031470000427362,
"count": 1,
"is_parallel": true,
"self": 0.0004031470000427362
},
"communicator.exchange": {
"total": 0.08847066899988931,
"count": 1,
"is_parallel": true,
"self": 0.08847066899988931
},
"steps_from_proto": {
"total": 0.0022433740000451508,
"count": 1,
"is_parallel": true,
"self": 0.0004353530005118955,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018080209995332552,
"count": 10,
"is_parallel": true,
"self": 0.0018080209995332552
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 254.29132604603024,
"count": 18199,
"is_parallel": true,
"self": 11.815392881122307,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.071917875947975,
"count": 18199,
"is_parallel": true,
"self": 6.071917875947975
},
"communicator.exchange": {
"total": 197.61625142095954,
"count": 18199,
"is_parallel": true,
"self": 197.61625142095954
},
"steps_from_proto": {
"total": 38.78776386800041,
"count": 18199,
"is_parallel": true,
"self": 7.338034303905488,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.449729564094923,
"count": 181990,
"is_parallel": true,
"self": 31.449729564094923
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001498769997851923,
"count": 1,
"self": 0.0001498769997851923,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 492.8462174319186,
"count": 732090,
"is_parallel": true,
"self": 16.682915483047964,
"children": {
"process_trajectory": {
"total": 273.23382139886803,
"count": 732090,
"is_parallel": true,
"self": 272.71914808186807,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5146733169999607,
"count": 4,
"is_parallel": true,
"self": 0.5146733169999607
}
}
},
"_update_policy": {
"total": 202.9294805500026,
"count": 90,
"is_parallel": true,
"self": 63.397671365000406,
"children": {
"TorchPPOOptimizer.update": {
"total": 139.5318091850022,
"count": 4587,
"is_parallel": true,
"self": 139.5318091850022
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09489322799981892,
"count": 1,
"self": 0.001561132999995607,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09333209499982331,
"count": 1,
"self": 0.09333209499982331
}
}
}
}
}
}
}