TheObamaMan's picture
First Push
7dcac75 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.915692150592804,
"min": 0.8971493244171143,
"max": 2.8431334495544434,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8702.73828125,
"min": 8702.73828125,
"max": 29022.70703125,
"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": 11.190634727478027,
"min": 0.23243631422519684,
"max": 11.192476272583008,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2182.173828125,
"min": 45.09264373779297,
"max": 2292.27978515625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06698502469956949,
"min": 0.06405827658617294,
"max": 0.07414227622953773,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26794009879827796,
"min": 0.25737889373547157,
"max": 0.3624813420191298,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18020639451695422,
"min": 0.11946770351941643,
"max": 0.29509485930788754,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7208255780678169,
"min": 0.47787081407766574,
"max": 1.4754742965394376,
"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": 21.75,
"min": 3.3863636363636362,
"max": 22.21818181818182,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 957.0,
"min": 149.0,
"max": 1222.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 21.75,
"min": 3.3863636363636362,
"max": 22.21818181818182,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 957.0,
"min": 149.0,
"max": 1222.0,
"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": "1744715180",
"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": "1744715616"
},
"total": 435.601154799,
"count": 1,
"self": 0.8032709309999291,
"children": {
"run_training.setup": {
"total": 0.023258284000007734,
"count": 1,
"self": 0.023258284000007734
},
"TrainerController.start_learning": {
"total": 434.7746255840001,
"count": 1,
"self": 0.35294497099948785,
"children": {
"TrainerController._reset_env": {
"total": 3.432813531000079,
"count": 1,
"self": 3.432813531000079
},
"TrainerController.advance": {
"total": 430.8498038090004,
"count": 18192,
"self": 0.3589899089879509,
"children": {
"env_step": {
"total": 305.8286485970075,
"count": 18192,
"self": 232.43760533200884,
"children": {
"SubprocessEnvManager._take_step": {
"total": 73.1810880860047,
"count": 18192,
"self": 1.300659757009612,
"children": {
"TorchPolicy.evaluate": {
"total": 71.8804283289951,
"count": 18192,
"self": 71.8804283289951
}
}
},
"workers": {
"total": 0.2099551789939369,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 433.170412345993,
"count": 18192,
"is_parallel": true,
"self": 229.4225476069846,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006812958999944385,
"count": 1,
"is_parallel": true,
"self": 0.005052101999694969,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017608570002494162,
"count": 10,
"is_parallel": true,
"self": 0.0017608570002494162
}
}
},
"UnityEnvironment.step": {
"total": 0.03748215599989635,
"count": 1,
"is_parallel": true,
"self": 0.0005980989998306541,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038309599995045573,
"count": 1,
"is_parallel": true,
"self": 0.00038309599995045573
},
"communicator.exchange": {
"total": 0.03472999800010257,
"count": 1,
"is_parallel": true,
"self": 0.03472999800010257
},
"steps_from_proto": {
"total": 0.0017709630000126708,
"count": 1,
"is_parallel": true,
"self": 0.00033310200024061487,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001437860999772056,
"count": 10,
"is_parallel": true,
"self": 0.001437860999772056
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 203.74786473900838,
"count": 18191,
"is_parallel": true,
"self": 9.771991896992404,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.384431669004812,
"count": 18191,
"is_parallel": true,
"self": 5.384431669004812
},
"communicator.exchange": {
"total": 156.57098957101198,
"count": 18191,
"is_parallel": true,
"self": 156.57098957101198
},
"steps_from_proto": {
"total": 32.020451601999184,
"count": 18191,
"is_parallel": true,
"self": 5.647827830001461,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.372623771997723,
"count": 181910,
"is_parallel": true,
"self": 26.372623771997723
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 124.66216530300494,
"count": 18192,
"self": 0.42727285200226106,
"children": {
"process_trajectory": {
"total": 27.772352715002057,
"count": 18192,
"self": 27.224135882002088,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5482168329999695,
"count": 4,
"self": 0.5482168329999695
}
}
},
"_update_policy": {
"total": 96.46253973600062,
"count": 90,
"self": 38.88897085800909,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.573568877991534,
"count": 4587,
"self": 57.573568877991534
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1189999895577785e-06,
"count": 1,
"self": 1.1189999895577785e-06
},
"TrainerController._save_models": {
"total": 0.13906215400015753,
"count": 1,
"self": 0.0011612670000431535,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13790088700011438,
"count": 1,
"self": 0.13790088700011438
}
}
}
}
}
}
}