JLTastet's picture
First Push
554a907 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7561957240104675,
"min": 0.7561957240104675,
"max": 2.839343309402466,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7186.88427734375,
"min": 7186.88427734375,
"max": 28984.017578125,
"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": 13.047882080078125,
"min": 0.40953901410102844,
"max": 13.128868103027344,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2544.3369140625,
"min": 79.45056915283203,
"max": 2678.2890625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07074478102829157,
"min": 0.06221769932587859,
"max": 0.0743487589036151,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2829791241131663,
"min": 0.24887079730351436,
"max": 0.3717437945180755,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18520694244287764,
"min": 0.1454676692259918,
"max": 0.27801933878777074,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7408277697715105,
"min": 0.5818706769039672,
"max": 1.3900966939388537,
"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": 25.59090909090909,
"min": 3.477272727272727,
"max": 25.945454545454545,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1126.0,
"min": 153.0,
"max": 1427.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.59090909090909,
"min": 3.477272727272727,
"max": 25.945454545454545,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1126.0,
"min": 153.0,
"max": 1427.0,
"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": "1742840312",
"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": "1742840830"
},
"total": 518.071196518,
"count": 1,
"self": 0.48314837400005217,
"children": {
"run_training.setup": {
"total": 0.025815000999955373,
"count": 1,
"self": 0.025815000999955373
},
"TrainerController.start_learning": {
"total": 517.562233143,
"count": 1,
"self": 0.48912684700201225,
"children": {
"TrainerController._reset_env": {
"total": 3.195532900000103,
"count": 1,
"self": 3.195532900000103
},
"TrainerController.advance": {
"total": 513.7691542499979,
"count": 18192,
"self": 0.5167581720014596,
"children": {
"env_step": {
"total": 371.62959902798866,
"count": 18192,
"self": 282.50263771297637,
"children": {
"SubprocessEnvManager._take_step": {
"total": 88.83756645700385,
"count": 18192,
"self": 1.5465515609810154,
"children": {
"TorchPolicy.evaluate": {
"total": 87.29101489602283,
"count": 18192,
"self": 87.29101489602283
}
}
},
"workers": {
"total": 0.2893948580084498,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 515.8033348239993,
"count": 18192,
"is_parallel": true,
"self": 268.77290627898947,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005590618999917751,
"count": 1,
"is_parallel": true,
"self": 0.003840534000005391,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017500849999123602,
"count": 10,
"is_parallel": true,
"self": 0.0017500849999123602
}
}
},
"UnityEnvironment.step": {
"total": 0.05760665900004369,
"count": 1,
"is_parallel": true,
"self": 0.0006563830002050963,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000469981999913216,
"count": 1,
"is_parallel": true,
"self": 0.000469981999913216
},
"communicator.exchange": {
"total": 0.05425521299991942,
"count": 1,
"is_parallel": true,
"self": 0.05425521299991942
},
"steps_from_proto": {
"total": 0.0022250810000059573,
"count": 1,
"is_parallel": true,
"self": 0.0003967779997537946,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018283030002521627,
"count": 10,
"is_parallel": true,
"self": 0.0018283030002521627
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 247.03042854500984,
"count": 18191,
"is_parallel": true,
"self": 11.717196177013989,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.62808025800291,
"count": 18191,
"is_parallel": true,
"self": 6.62808025800291
},
"communicator.exchange": {
"total": 189.84171895899522,
"count": 18191,
"is_parallel": true,
"self": 189.84171895899522
},
"steps_from_proto": {
"total": 38.843433150997726,
"count": 18191,
"is_parallel": true,
"self": 7.143242132995624,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.7001910180021,
"count": 181910,
"is_parallel": true,
"self": 31.7001910180021
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 141.62279705000776,
"count": 18192,
"self": 0.5881452940119516,
"children": {
"process_trajectory": {
"total": 31.972624187995507,
"count": 18192,
"self": 31.476345421995575,
"children": {
"RLTrainer._checkpoint": {
"total": 0.49627876599993215,
"count": 4,
"self": 0.49627876599993215
}
}
},
"_update_policy": {
"total": 109.0620275680003,
"count": 90,
"self": 43.97129366000195,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.09073390799836,
"count": 4587,
"self": 65.09073390799836
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3080000371701317e-06,
"count": 1,
"self": 1.3080000371701317e-06
},
"TrainerController._save_models": {
"total": 0.108417837999923,
"count": 1,
"self": 0.0011115439997411158,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10730629400018188,
"count": 1,
"self": 0.10730629400018188
}
}
}
}
}
}
}