dgenes's picture
First Push
000323b verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.773022472858429,
"min": 0.7416322827339172,
"max": 2.849980592727661,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7346.8056640625,
"min": 7346.8056640625,
"max": 29092.6015625,
"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": 12.898033142089844,
"min": 0.3636086583137512,
"max": 12.95396900177002,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2515.116455078125,
"min": 70.54007720947266,
"max": 2642.609619140625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07345888682860224,
"min": 0.06362761501976125,
"max": 0.0750107883804423,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.293835547314409,
"min": 0.25545446261964444,
"max": 0.36804622328496656,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21354448064869525,
"min": 0.135999796985119,
"max": 0.28605228852407605,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.854177922594781,
"min": 0.543999187940476,
"max": 1.4081158015657873,
"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": 25.136363636363637,
"min": 3.8863636363636362,
"max": 25.40909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1106.0,
"min": 171.0,
"max": 1395.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.136363636363637,
"min": 3.8863636363636362,
"max": 25.40909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1106.0,
"min": 171.0,
"max": 1395.0,
"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": "1770657990",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1770658422"
},
"total": 432.75440368,
"count": 1,
"self": 0.43630364000000554,
"children": {
"run_training.setup": {
"total": 0.026050020999946355,
"count": 1,
"self": 0.026050020999946355
},
"TrainerController.start_learning": {
"total": 432.29205001900004,
"count": 1,
"self": 0.3556986500041148,
"children": {
"TrainerController._reset_env": {
"total": 2.6698415690000274,
"count": 1,
"self": 2.6698415690000274
},
"TrainerController.advance": {
"total": 429.1902200159959,
"count": 18192,
"self": 0.37374562999661975,
"children": {
"env_step": {
"total": 311.2891226369977,
"count": 18192,
"self": 243.60022930401806,
"children": {
"SubprocessEnvManager._take_step": {
"total": 67.48006430300416,
"count": 18192,
"self": 1.2258770170001299,
"children": {
"TorchPolicy.evaluate": {
"total": 66.25418728600403,
"count": 18192,
"self": 66.25418728600403
}
}
},
"workers": {
"total": 0.20882902997550445,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 430.45227702001966,
"count": 18192,
"is_parallel": true,
"self": 216.1021008660241,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004743176999909338,
"count": 1,
"is_parallel": true,
"self": 0.0034091219999936584,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013340549999156792,
"count": 10,
"is_parallel": true,
"self": 0.0013340549999156792
}
}
},
"UnityEnvironment.step": {
"total": 0.03549005599984412,
"count": 1,
"is_parallel": true,
"self": 0.000606197000024622,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004000310000265017,
"count": 1,
"is_parallel": true,
"self": 0.0004000310000265017
},
"communicator.exchange": {
"total": 0.03264266799988036,
"count": 1,
"is_parallel": true,
"self": 0.03264266799988036
},
"steps_from_proto": {
"total": 0.0018411599999126338,
"count": 1,
"is_parallel": true,
"self": 0.0003698499999700289,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001471309999942605,
"count": 10,
"is_parallel": true,
"self": 0.001471309999942605
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 214.35017615399556,
"count": 18191,
"is_parallel": true,
"self": 10.098903191954605,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.317343465009117,
"count": 18191,
"is_parallel": true,
"self": 5.317343465009117
},
"communicator.exchange": {
"total": 163.09496613501392,
"count": 18191,
"is_parallel": true,
"self": 163.09496613501392
},
"steps_from_proto": {
"total": 35.83896336201792,
"count": 18191,
"is_parallel": true,
"self": 6.366978557011862,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.47198480500606,
"count": 181910,
"is_parallel": true,
"self": 29.47198480500606
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 117.52735174900158,
"count": 18192,
"self": 0.42073865900033525,
"children": {
"process_trajectory": {
"total": 25.75299295500122,
"count": 18192,
"self": 25.155520898001214,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5974720570000045,
"count": 4,
"self": 0.5974720570000045
}
}
},
"_update_policy": {
"total": 91.35362013500003,
"count": 90,
"self": 38.02084581399822,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.33277432100181,
"count": 4587,
"self": 53.33277432100181
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.055999973686994e-06,
"count": 1,
"self": 1.055999973686994e-06
},
"TrainerController._save_models": {
"total": 0.07628872800000863,
"count": 1,
"self": 0.0007711199998539087,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07551760800015472,
"count": 1,
"self": 0.07551760800015472
}
}
}
}
}
}
}