ValentinGuigon's picture
First Push
0a6c9a1 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9689862728118896,
"min": 0.9689862728118896,
"max": 2.8658132553100586,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9262.5400390625,
"min": 9262.5400390625,
"max": 29380.31640625,
"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": 12.741747856140137,
"min": 0.23367734253406525,
"max": 12.741747856140137,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2484.640869140625,
"min": 45.333404541015625,
"max": 2588.576416015625,
"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": 0.06970400335148061,
"min": 0.06247576518088703,
"max": 0.07457993937628893,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27881601340592244,
"min": 0.24990306072354812,
"max": 0.37289969688144464,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1933652034723291,
"min": 0.1447921790839995,
"max": 0.2696718957786467,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7734608138893164,
"min": 0.579168716335998,
"max": 1.3053849880017485,
"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": 24.954545454545453,
"min": 3.772727272727273,
"max": 25.527272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1098.0,
"min": 166.0,
"max": 1404.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.954545454545453,
"min": 3.772727272727273,
"max": 25.527272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1098.0,
"min": 166.0,
"max": 1404.0,
"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": "1727295660",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1727296250"
},
"total": 589.634317605,
"count": 1,
"self": 0.48056243399992127,
"children": {
"run_training.setup": {
"total": 0.06266986400004271,
"count": 1,
"self": 0.06266986400004271
},
"TrainerController.start_learning": {
"total": 589.0910853070001,
"count": 1,
"self": 0.8245578439949668,
"children": {
"TrainerController._reset_env": {
"total": 2.8088288929999976,
"count": 1,
"self": 2.8088288929999976
},
"TrainerController.advance": {
"total": 585.3683811900054,
"count": 18203,
"self": 0.40521792700076276,
"children": {
"env_step": {
"total": 584.9631632630046,
"count": 18203,
"self": 451.2364454590101,
"children": {
"SubprocessEnvManager._take_step": {
"total": 133.31581452199737,
"count": 18203,
"self": 2.26870294800068,
"children": {
"TorchPolicy.evaluate": {
"total": 131.0471115739967,
"count": 18203,
"self": 131.0471115739967
}
}
},
"workers": {
"total": 0.4109032819971503,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 587.177286535996,
"count": 18203,
"is_parallel": true,
"self": 275.7411407680001,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0024441529999990053,
"count": 1,
"is_parallel": true,
"self": 0.0008308999999826483,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001613253000016357,
"count": 10,
"is_parallel": true,
"self": 0.001613253000016357
}
}
},
"UnityEnvironment.step": {
"total": 0.043128443000000516,
"count": 1,
"is_parallel": true,
"self": 0.0008736490000273989,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047804899998027395,
"count": 1,
"is_parallel": true,
"self": 0.00047804899998027395
},
"communicator.exchange": {
"total": 0.039470477999998366,
"count": 1,
"is_parallel": true,
"self": 0.039470477999998366
},
"steps_from_proto": {
"total": 0.0023062669999944774,
"count": 1,
"is_parallel": true,
"self": 0.00046096999994915677,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018452970000453206,
"count": 10,
"is_parallel": true,
"self": 0.0018452970000453206
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 311.4361457679959,
"count": 18202,
"is_parallel": true,
"self": 14.718462376994069,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.771654140996191,
"count": 18202,
"is_parallel": true,
"self": 7.771654140996191
},
"communicator.exchange": {
"total": 245.39587206000886,
"count": 18202,
"is_parallel": true,
"self": 245.39587206000886
},
"steps_from_proto": {
"total": 43.55015718999681,
"count": 18202,
"is_parallel": true,
"self": 8.763902459990732,
"children": {
"_process_rank_one_or_two_observation": {
"total": 34.78625473000608,
"count": 182020,
"is_parallel": true,
"self": 34.78625473000608
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00024821099987093476,
"count": 1,
"self": 0.00024821099987093476,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 578.4714073300518,
"count": 789001,
"is_parallel": true,
"self": 17.377848648992085,
"children": {
"process_trajectory": {
"total": 310.2115030860596,
"count": 789001,
"is_parallel": true,
"self": 309.30127373705983,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9102293489997919,
"count": 4,
"is_parallel": true,
"self": 0.9102293489997919
}
}
},
"_update_policy": {
"total": 250.8820555950001,
"count": 90,
"is_parallel": true,
"self": 72.27646597699982,
"children": {
"TorchPPOOptimizer.update": {
"total": 178.6055896180003,
"count": 4587,
"is_parallel": true,
"self": 178.6055896180003
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08906916899991302,
"count": 1,
"self": 0.001455699999951321,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0876134689999617,
"count": 1,
"self": 0.0876134689999617
}
}
}
}
}
}
}