eulpicard's picture
First Push
0ed95b3 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8870714902877808,
"min": 0.8791836500167847,
"max": 2.85666823387146,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8479.5166015625,
"min": 8479.5166015625,
"max": 29255.138671875,
"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": 12.79212474822998,
"min": 0.3811277151107788,
"max": 12.79212474822998,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2494.46435546875,
"min": 73.93877410888672,
"max": 2593.60107421875,
"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": 0.06840314454023552,
"min": 0.06552238330333042,
"max": 0.07671334125720229,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2736125781609421,
"min": 0.26374776593208893,
"max": 0.38356670628601147,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.23653873618619115,
"min": 0.14336337334951205,
"max": 0.2935466664094551,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9461549447447646,
"min": 0.5734534933980482,
"max": 1.4009876683646558,
"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": 24.931818181818183,
"min": 3.8636363636363638,
"max": 25.227272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1097.0,
"min": 170.0,
"max": 1386.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.931818181818183,
"min": 3.8636363636363638,
"max": 25.227272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1097.0,
"min": 170.0,
"max": 1386.0,
"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": "1713814534",
"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": "1713814995"
},
"total": 460.86134186699996,
"count": 1,
"self": 0.4356669599997076,
"children": {
"run_training.setup": {
"total": 0.05311868500007222,
"count": 1,
"self": 0.05311868500007222
},
"TrainerController.start_learning": {
"total": 460.3725562220002,
"count": 1,
"self": 0.5826795800010132,
"children": {
"TrainerController._reset_env": {
"total": 2.8921644489998926,
"count": 1,
"self": 2.8921644489998926
},
"TrainerController.advance": {
"total": 456.80891914399945,
"count": 18200,
"self": 0.2801795900045363,
"children": {
"env_step": {
"total": 456.5287395539949,
"count": 18200,
"self": 294.9403221169514,
"children": {
"SubprocessEnvManager._take_step": {
"total": 161.2886256730194,
"count": 18200,
"self": 1.538395750054633,
"children": {
"TorchPolicy.evaluate": {
"total": 159.75022992296476,
"count": 18200,
"self": 159.75022992296476
}
}
},
"workers": {
"total": 0.2997917640241212,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 459.05942933401,
"count": 18200,
"is_parallel": true,
"self": 231.1242489970175,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0053600050000568444,
"count": 1,
"is_parallel": true,
"self": 0.0036480050002865028,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017119999997703417,
"count": 10,
"is_parallel": true,
"self": 0.0017119999997703417
}
}
},
"UnityEnvironment.step": {
"total": 0.03812552599993069,
"count": 1,
"is_parallel": true,
"self": 0.0006372989998908452,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004451439999684226,
"count": 1,
"is_parallel": true,
"self": 0.0004451439999684226
},
"communicator.exchange": {
"total": 0.03510592400016321,
"count": 1,
"is_parallel": true,
"self": 0.03510592400016321
},
"steps_from_proto": {
"total": 0.0019371589999082062,
"count": 1,
"is_parallel": true,
"self": 0.00038466799946945684,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015524910004387493,
"count": 10,
"is_parallel": true,
"self": 0.0015524910004387493
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 227.93518033699252,
"count": 18199,
"is_parallel": true,
"self": 10.438952736991496,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.645775277013854,
"count": 18199,
"is_parallel": true,
"self": 5.645775277013854
},
"communicator.exchange": {
"total": 176.19368698800986,
"count": 18199,
"is_parallel": true,
"self": 176.19368698800986
},
"steps_from_proto": {
"total": 35.65676533497731,
"count": 18199,
"is_parallel": true,
"self": 6.787178462896918,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.86958687208039,
"count": 181990,
"is_parallel": true,
"self": 28.86958687208039
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013319999970917706,
"count": 1,
"self": 0.00013319999970917706,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 450.99868046385063,
"count": 689868,
"is_parallel": true,
"self": 14.956820386017625,
"children": {
"process_trajectory": {
"total": 250.51239745483167,
"count": 689868,
"is_parallel": true,
"self": 249.9108692188313,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6015282360003766,
"count": 4,
"is_parallel": true,
"self": 0.6015282360003766
}
}
},
"_update_policy": {
"total": 185.52946262300134,
"count": 90,
"is_parallel": true,
"self": 53.598227020005424,
"children": {
"TorchPPOOptimizer.update": {
"total": 131.9312356029959,
"count": 4587,
"is_parallel": true,
"self": 131.9312356029959
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08865984900012336,
"count": 1,
"self": 0.0009031069998854946,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08775674200023786,
"count": 1,
"self": 0.08775674200023786
}
}
}
}
}
}
}