ajmalmahmood's picture
First Push
b830af6 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8461096286773682,
"min": 0.8461096286773682,
"max": 2.8463950157165527,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8041.42578125,
"min": 8041.42578125,
"max": 29056.0,
"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": 12.998404502868652,
"min": 0.417167067527771,
"max": 12.998404502868652,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2534.68896484375,
"min": 80.93041229248047,
"max": 2645.609375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0723845539709654,
"min": 0.06348210811961955,
"max": 0.07413573313198296,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2895382158838616,
"min": 0.2539284324784782,
"max": 0.3598250988813793,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18717896193265918,
"min": 0.12653148304282996,
"max": 0.2642428851595112,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7487158477306367,
"min": 0.5061259321713198,
"max": 1.3139154522442351,
"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": 25.863636363636363,
"min": 3.3181818181818183,
"max": 25.863636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1138.0,
"min": 146.0,
"max": 1396.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.863636363636363,
"min": 3.3181818181818183,
"max": 25.863636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1138.0,
"min": 146.0,
"max": 1396.0,
"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": "1747852481",
"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 --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1747852896"
},
"total": 415.3373281610002,
"count": 1,
"self": 0.6596961309996914,
"children": {
"run_training.setup": {
"total": 0.020678683000369347,
"count": 1,
"self": 0.020678683000369347
},
"TrainerController.start_learning": {
"total": 414.6569533470001,
"count": 1,
"self": 0.3266772069782746,
"children": {
"TrainerController._reset_env": {
"total": 2.0285601109999334,
"count": 1,
"self": 2.0285601109999334
},
"TrainerController.advance": {
"total": 412.1799419300214,
"count": 18192,
"self": 0.35157116814207257,
"children": {
"env_step": {
"total": 293.1132387019452,
"count": 18192,
"self": 224.04927773092004,
"children": {
"SubprocessEnvManager._take_step": {
"total": 68.85565302601754,
"count": 18192,
"self": 1.2266791019583252,
"children": {
"TorchPolicy.evaluate": {
"total": 67.62897392405921,
"count": 18192,
"self": 67.62897392405921
}
}
},
"workers": {
"total": 0.2083079450076184,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 413.13712017293983,
"count": 18192,
"is_parallel": true,
"self": 216.13651815292633,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002031514000009338,
"count": 1,
"is_parallel": true,
"self": 0.0006132280013844138,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001418285998624924,
"count": 10,
"is_parallel": true,
"self": 0.001418285998624924
}
}
},
"UnityEnvironment.step": {
"total": 0.034528010999565595,
"count": 1,
"is_parallel": true,
"self": 0.0006049989997336525,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004571290000967565,
"count": 1,
"is_parallel": true,
"self": 0.0004571290000967565
},
"communicator.exchange": {
"total": 0.03160041800038016,
"count": 1,
"is_parallel": true,
"self": 0.03160041800038016
},
"steps_from_proto": {
"total": 0.0018654649993550265,
"count": 1,
"is_parallel": true,
"self": 0.00037574900034087477,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014897159990141517,
"count": 10,
"is_parallel": true,
"self": 0.0014897159990141517
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 197.0006020200135,
"count": 18191,
"is_parallel": true,
"self": 9.523424058021192,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.4105021819596,
"count": 18191,
"is_parallel": true,
"self": 5.4105021819596
},
"communicator.exchange": {
"total": 151.23969691596722,
"count": 18191,
"is_parallel": true,
"self": 151.23969691596722
},
"steps_from_proto": {
"total": 30.826978864065495,
"count": 18191,
"is_parallel": true,
"self": 5.388668132802195,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.4383107312633,
"count": 181910,
"is_parallel": true,
"self": 25.4383107312633
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 118.71513205993415,
"count": 18192,
"self": 0.3893119559324987,
"children": {
"process_trajectory": {
"total": 26.626253579004697,
"count": 18192,
"self": 26.215517050006383,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4107365289983136,
"count": 4,
"self": 0.4107365289983136
}
}
},
"_update_policy": {
"total": 91.69956652499695,
"count": 90,
"self": 36.787112819057256,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.9124537059397,
"count": 4587,
"self": 54.9124537059397
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.422000423190184e-06,
"count": 1,
"self": 1.422000423190184e-06
},
"TrainerController._save_models": {
"total": 0.12177267700008088,
"count": 1,
"self": 0.0013809749998472398,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12039170200023364,
"count": 1,
"self": 0.12039170200023364
}
}
}
}
}
}
}