rjhuang's picture
First Push
0a97c60 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8509201407432556,
"min": 0.8367247581481934,
"max": 2.854109287261963,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8087.14501953125,
"min": 8069.1845703125,
"max": 29134.748046875,
"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": 12.970890998840332,
"min": 0.4478744864463806,
"max": 12.970890998840332,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2529.32373046875,
"min": 86.88764953613281,
"max": 2637.509033203125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06959402017145846,
"min": 0.06244319331320487,
"max": 0.07482020365982774,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27837608068583386,
"min": 0.2497727732528195,
"max": 0.37410101829913867,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19111909735582622,
"min": 0.1407906437023342,
"max": 0.2894211848284684,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7644763894233049,
"min": 0.5631625748093368,
"max": 1.4132258661237418,
"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": 25.522727272727273,
"min": 4.113636363636363,
"max": 25.636363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1123.0,
"min": 181.0,
"max": 1408.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.522727272727273,
"min": 4.113636363636363,
"max": 25.636363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1123.0,
"min": 181.0,
"max": 1408.0,
"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": "1741086110",
"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": "1741086545"
},
"total": 435.46848627400004,
"count": 1,
"self": 0.4487651959999539,
"children": {
"run_training.setup": {
"total": 0.02399986800003262,
"count": 1,
"self": 0.02399986800003262
},
"TrainerController.start_learning": {
"total": 434.99572121000006,
"count": 1,
"self": 0.4202830839997205,
"children": {
"TrainerController._reset_env": {
"total": 3.2139095669999733,
"count": 1,
"self": 3.2139095669999733
},
"TrainerController.advance": {
"total": 431.2732623610003,
"count": 18192,
"self": 0.43243902300019954,
"children": {
"env_step": {
"total": 306.38622482200327,
"count": 18192,
"self": 233.37177724500225,
"children": {
"SubprocessEnvManager._take_step": {
"total": 72.77751169899693,
"count": 18192,
"self": 1.3094653490001065,
"children": {
"TorchPolicy.evaluate": {
"total": 71.46804634999683,
"count": 18192,
"self": 71.46804634999683
}
}
},
"workers": {
"total": 0.23693587800408977,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 433.3788880260053,
"count": 18192,
"is_parallel": true,
"self": 229.71097384700772,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005527703000041129,
"count": 1,
"is_parallel": true,
"self": 0.0040514609999604545,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014762420000806742,
"count": 10,
"is_parallel": true,
"self": 0.0014762420000806742
}
}
},
"UnityEnvironment.step": {
"total": 0.03444930399996338,
"count": 1,
"is_parallel": true,
"self": 0.000600719000033223,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003786789999935536,
"count": 1,
"is_parallel": true,
"self": 0.0003786789999935536
},
"communicator.exchange": {
"total": 0.031512540999983685,
"count": 1,
"is_parallel": true,
"self": 0.031512540999983685
},
"steps_from_proto": {
"total": 0.0019573649999529152,
"count": 1,
"is_parallel": true,
"self": 0.00037084199982473365,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015865230001281816,
"count": 10,
"is_parallel": true,
"self": 0.0015865230001281816
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 203.6679141789976,
"count": 18191,
"is_parallel": true,
"self": 9.860725756989382,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.3277510770050185,
"count": 18191,
"is_parallel": true,
"self": 5.3277510770050185
},
"communicator.exchange": {
"total": 157.4115654760044,
"count": 18191,
"is_parallel": true,
"self": 157.4115654760044
},
"steps_from_proto": {
"total": 31.067871868998793,
"count": 18191,
"is_parallel": true,
"self": 5.705864664972694,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.3620072040261,
"count": 181910,
"is_parallel": true,
"self": 25.3620072040261
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 124.45459851599685,
"count": 18192,
"self": 0.5043801310029039,
"children": {
"process_trajectory": {
"total": 26.993972001994337,
"count": 18192,
"self": 26.442585949994452,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5513860519998843,
"count": 4,
"self": 0.5513860519998843
}
}
},
"_update_policy": {
"total": 96.95624638299961,
"count": 90,
"self": 38.553055018998066,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.40319136400154,
"count": 4587,
"self": 58.40319136400154
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0640000027706265e-06,
"count": 1,
"self": 1.0640000027706265e-06
},
"TrainerController._save_models": {
"total": 0.08826513400003932,
"count": 1,
"self": 0.0009118380000927573,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08735329599994657,
"count": 1,
"self": 0.08735329599994657
}
}
}
}
}
}
}