reeeemo's picture
First Push
ff20f33 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9529734253883362,
"min": 0.9469109177589417,
"max": 2.8545427322387695,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9057.0595703125,
"min": 9057.0595703125,
"max": 29139.171875,
"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": 12.72038745880127,
"min": 0.4274882674217224,
"max": 12.741671562194824,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2480.4755859375,
"min": 82.93272399902344,
"max": 2609.065673828125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0686016549014169,
"min": 0.06399813718099703,
"max": 0.07646553400927052,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2744066196056676,
"min": 0.25599254872398813,
"max": 0.37953253750924437,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19460112265512053,
"min": 0.13016433298231705,
"max": 0.31563861207926974,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7784044906204821,
"min": 0.5206573319292682,
"max": 1.556473227984765,
"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": 25.454545454545453,
"min": 3.772727272727273,
"max": 25.568181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1120.0,
"min": 166.0,
"max": 1378.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.454545454545453,
"min": 3.772727272727273,
"max": 25.568181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1120.0,
"min": 166.0,
"max": 1378.0,
"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": "1767217155",
"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": "1767217758"
},
"total": 602.182884749,
"count": 1,
"self": 0.5908706380000694,
"children": {
"run_training.setup": {
"total": 0.03578184799994233,
"count": 1,
"self": 0.03578184799994233
},
"TrainerController.start_learning": {
"total": 601.556232263,
"count": 1,
"self": 0.6360450550059795,
"children": {
"TrainerController._reset_env": {
"total": 3.783011137000017,
"count": 1,
"self": 3.783011137000017
},
"TrainerController.advance": {
"total": 597.0492761699941,
"count": 18192,
"self": 0.6901569249828299,
"children": {
"env_step": {
"total": 422.76455334500304,
"count": 18192,
"self": 364.0984361490133,
"children": {
"SubprocessEnvManager._take_step": {
"total": 58.24525965099667,
"count": 18192,
"self": 2.1058438419830736,
"children": {
"TorchPolicy.evaluate": {
"total": 56.1394158090136,
"count": 18192,
"self": 56.1394158090136
}
}
},
"workers": {
"total": 0.42085754499305494,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 598.4741912670032,
"count": 18192,
"is_parallel": true,
"self": 284.6335837039935,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006291849000035654,
"count": 1,
"is_parallel": true,
"self": 0.004504120000206058,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017877289998295964,
"count": 10,
"is_parallel": true,
"self": 0.0017877289998295964
}
}
},
"UnityEnvironment.step": {
"total": 0.10563440700002502,
"count": 1,
"is_parallel": true,
"self": 0.0014591620000601324,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0011430099999643062,
"count": 1,
"is_parallel": true,
"self": 0.0011430099999643062
},
"communicator.exchange": {
"total": 0.09802061699997466,
"count": 1,
"is_parallel": true,
"self": 0.09802061699997466
},
"steps_from_proto": {
"total": 0.005011618000025919,
"count": 1,
"is_parallel": true,
"self": 0.0013667550000491246,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0036448629999767945,
"count": 10,
"is_parallel": true,
"self": 0.0036448629999767945
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 313.8406075630097,
"count": 18191,
"is_parallel": true,
"self": 14.9079906850111,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.667595491997304,
"count": 18191,
"is_parallel": true,
"self": 7.667595491997304
},
"communicator.exchange": {
"total": 242.67071363400714,
"count": 18191,
"is_parallel": true,
"self": 242.67071363400714
},
"steps_from_proto": {
"total": 48.594307751994165,
"count": 18191,
"is_parallel": true,
"self": 8.76021223498401,
"children": {
"_process_rank_one_or_two_observation": {
"total": 39.834095517010155,
"count": 181910,
"is_parallel": true,
"self": 39.834095517010155
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 173.5945659000082,
"count": 18192,
"self": 0.8289344330031554,
"children": {
"process_trajectory": {
"total": 32.044246753005154,
"count": 18192,
"self": 31.47595272700528,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5682940259998759,
"count": 4,
"self": 0.5682940259998759
}
}
},
"_update_policy": {
"total": 140.7213847139999,
"count": 90,
"self": 51.58031867500006,
"children": {
"TorchPPOOptimizer.update": {
"total": 89.14106603899984,
"count": 4587,
"self": 89.14106603899984
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0839999049494509e-06,
"count": 1,
"self": 1.0839999049494509e-06
},
"TrainerController._save_models": {
"total": 0.08789881699999569,
"count": 1,
"self": 0.0015875030001097912,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0863113139998859,
"count": 1,
"self": 0.0863113139998859
}
}
}
}
}
}
}