Taikuchou's picture
First Push
7cddee9 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8355684876441956,
"min": 0.8119158148765564,
"max": 2.8095123767852783,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7941.24267578125,
"min": 7941.24267578125,
"max": 28679.501953125,
"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": 11.897113800048828,
"min": 0.49053263664245605,
"max": 11.953622817993164,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2319.937255859375,
"min": 95.163330078125,
"max": 2438.5390625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07257432560094029,
"min": 0.06380686206730567,
"max": 0.07587433477387735,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29029730240376117,
"min": 0.25522744826922267,
"max": 0.3729973008003606,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17861725828226874,
"min": 0.13600742669579774,
"max": 0.29668514766529497,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.714469033129075,
"min": 0.544029706783191,
"max": 1.4024975887116264,
"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.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.Environment.CumulativeReward.mean": {
"value": 22.886363636363637,
"min": 3.840909090909091,
"max": 23.69090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1007.0,
"min": 169.0,
"max": 1303.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 22.886363636363637,
"min": 3.840909090909091,
"max": 23.69090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1007.0,
"min": 169.0,
"max": 1303.0,
"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": "1739110423",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.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": "1739110868"
},
"total": 444.87695828899996,
"count": 1,
"self": 0.43824597099978746,
"children": {
"run_training.setup": {
"total": 0.023299177000126292,
"count": 1,
"self": 0.023299177000126292
},
"TrainerController.start_learning": {
"total": 444.41541314100004,
"count": 1,
"self": 0.3873132829946826,
"children": {
"TrainerController._reset_env": {
"total": 2.180460430000039,
"count": 1,
"self": 2.180460430000039
},
"TrainerController.advance": {
"total": 441.7574625320051,
"count": 18192,
"self": 0.38672966002900466,
"children": {
"env_step": {
"total": 315.24083417598945,
"count": 18192,
"self": 238.95211770601554,
"children": {
"SubprocessEnvManager._take_step": {
"total": 76.06532997199452,
"count": 18192,
"self": 1.337007551984243,
"children": {
"TorchPolicy.evaluate": {
"total": 74.72832242001027,
"count": 18192,
"self": 74.72832242001027
}
}
},
"workers": {
"total": 0.2233864979793907,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 442.7981935120115,
"count": 18192,
"is_parallel": true,
"self": 233.51584031601192,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002377565999950093,
"count": 1,
"is_parallel": true,
"self": 0.0007620559999850229,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016155099999650702,
"count": 10,
"is_parallel": true,
"self": 0.0016155099999650702
}
}
},
"UnityEnvironment.step": {
"total": 0.07050332999983766,
"count": 1,
"is_parallel": true,
"self": 0.0005632540000988229,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003507539997826825,
"count": 1,
"is_parallel": true,
"self": 0.0003507539997826825
},
"communicator.exchange": {
"total": 0.0679586849998941,
"count": 1,
"is_parallel": true,
"self": 0.0679586849998941
},
"steps_from_proto": {
"total": 0.0016306370000620518,
"count": 1,
"is_parallel": true,
"self": 0.00031067000008988543,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013199669999721664,
"count": 10,
"is_parallel": true,
"self": 0.0013199669999721664
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 209.28235319599958,
"count": 18191,
"is_parallel": true,
"self": 9.797535779978261,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.535155800020675,
"count": 18191,
"is_parallel": true,
"self": 5.535155800020675
},
"communicator.exchange": {
"total": 161.11343656401505,
"count": 18191,
"is_parallel": true,
"self": 161.11343656401505
},
"steps_from_proto": {
"total": 32.83622505198559,
"count": 18191,
"is_parallel": true,
"self": 5.863591172984798,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.972633879000796,
"count": 181910,
"is_parallel": true,
"self": 26.972633879000796
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 126.12989869598664,
"count": 18192,
"self": 0.45291778500859436,
"children": {
"process_trajectory": {
"total": 28.320393301976992,
"count": 18192,
"self": 27.804754759977186,
"children": {
"RLTrainer._checkpoint": {
"total": 0.515638541999806,
"count": 4,
"self": 0.515638541999806
}
}
},
"_update_policy": {
"total": 97.35658760900105,
"count": 90,
"self": 39.099419263020536,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.25716834598052,
"count": 4587,
"self": 58.25716834598052
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4090001059230417e-06,
"count": 1,
"self": 1.4090001059230417e-06
},
"TrainerController._save_models": {
"total": 0.09017548700012412,
"count": 1,
"self": 0.0008747619999667222,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0893007250001574,
"count": 1,
"self": 0.0893007250001574
}
}
}
}
}
}
}