Rryay12's picture
First Push
ad9a1f4
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.5947715044021606,
"min": 1.5947715044021606,
"max": 2.8739395141601562,
"count": 10
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 16261.884765625,
"min": 16150.6591796875,
"max": 29463.626953125,
"count": 10
},
"SnowballTarget.Step.mean": {
"value": 99960.0,
"min": 9952.0,
"max": 99960.0,
"count": 10
},
"SnowballTarget.Step.sum": {
"value": 99960.0,
"min": 9952.0,
"max": 99960.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 9.422186851501465,
"min": 0.2172641009092331,
"max": 9.422186851501465,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1922.1260986328125,
"min": 42.149234771728516,
"max": 1922.1260986328125,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07064669740847974,
"min": 0.05785576576718264,
"max": 0.07474350637601353,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3532334870423987,
"min": 0.23142306306873056,
"max": 0.3678528154839524,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.27150143747236216,
"min": 0.10615547957565344,
"max": 0.3097439442633414,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.3575071873618108,
"min": 0.42462191830261375,
"max": 1.4047094525075428,
"count": 10
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.6464094511999996e-05,
"min": 1.6464094511999996e-05,
"max": 0.000283764005412,
"count": 10
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 8.232047255999999e-05,
"min": 8.232047255999999e-05,
"max": 0.00127032007656,
"count": 10
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.105488,
"min": 0.105488,
"max": 0.194588,
"count": 10
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.52744,
"min": 0.4615520000000001,
"max": 0.92344,
"count": 10
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0002838512,
"min": 0.0002838512,
"max": 0.0047299412,
"count": 10
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.001419256,
"min": 0.001419256,
"max": 0.021179656,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 19.98181818181818,
"min": 3.0454545454545454,
"max": 19.98181818181818,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1099.0,
"min": 134.0,
"max": 1099.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 19.98181818181818,
"min": 3.0454545454545454,
"max": 19.98181818181818,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1099.0,
"min": 134.0,
"max": 1099.0,
"count": 10
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1687856040",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1687856282"
},
"total": 241.888672767,
"count": 1,
"self": 0.42421218799995586,
"children": {
"run_training.setup": {
"total": 0.06910632499989333,
"count": 1,
"self": 0.06910632499989333
},
"TrainerController.start_learning": {
"total": 241.39535425400015,
"count": 1,
"self": 0.3033404309966272,
"children": {
"TrainerController._reset_env": {
"total": 4.484206846000006,
"count": 1,
"self": 4.484206846000006
},
"TrainerController.advance": {
"total": 236.46748248400354,
"count": 9139,
"self": 0.13629149900305038,
"children": {
"env_step": {
"total": 236.3311909850005,
"count": 9139,
"self": 173.73633080000445,
"children": {
"SubprocessEnvManager._take_step": {
"total": 62.465369074999444,
"count": 9139,
"self": 0.9124179580015834,
"children": {
"TorchPolicy.evaluate": {
"total": 61.55295111699786,
"count": 9139,
"self": 61.55295111699786
}
}
},
"workers": {
"total": 0.12949110999659297,
"count": 9139,
"self": 0.0,
"children": {
"worker_root": {
"total": 240.45423524800174,
"count": 9139,
"is_parallel": true,
"self": 113.35669500499898,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00296787900003892,
"count": 1,
"is_parallel": true,
"self": 0.0007521589999441858,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002215720000094734,
"count": 10,
"is_parallel": true,
"self": 0.002215720000094734
}
}
},
"UnityEnvironment.step": {
"total": 0.04901322099999561,
"count": 1,
"is_parallel": true,
"self": 0.0006261739999899874,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004158179999649292,
"count": 1,
"is_parallel": true,
"self": 0.0004158179999649292
},
"communicator.exchange": {
"total": 0.04587392500002352,
"count": 1,
"is_parallel": true,
"self": 0.04587392500002352
},
"steps_from_proto": {
"total": 0.002097304000017175,
"count": 1,
"is_parallel": true,
"self": 0.0003626770001119439,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001734626999905231,
"count": 10,
"is_parallel": true,
"self": 0.001734626999905231
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 127.09754024300275,
"count": 9138,
"is_parallel": true,
"self": 5.210997367997265,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.6537896650021366,
"count": 9138,
"is_parallel": true,
"self": 2.6537896650021366
},
"communicator.exchange": {
"total": 101.5433268910025,
"count": 9138,
"is_parallel": true,
"self": 101.5433268910025
},
"steps_from_proto": {
"total": 17.68942631900086,
"count": 9138,
"is_parallel": true,
"self": 3.2541413999857696,
"children": {
"_process_rank_one_or_two_observation": {
"total": 14.43528491901509,
"count": 91380,
"is_parallel": true,
"self": 14.43528491901509
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0002891130000080011,
"count": 1,
"self": 0.0002891130000080011,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 234.77650554200477,
"count": 222573,
"is_parallel": true,
"self": 4.771669926990398,
"children": {
"process_trajectory": {
"total": 128.50512757701426,
"count": 222573,
"is_parallel": true,
"self": 127.55124638801419,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9538811890000716,
"count": 2,
"is_parallel": true,
"self": 0.9538811890000716
}
}
},
"_update_policy": {
"total": 101.49970803800011,
"count": 45,
"is_parallel": true,
"self": 40.78137202700077,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.71833601099934,
"count": 2292,
"is_parallel": true,
"self": 60.71833601099934
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14003537999997206,
"count": 1,
"self": 0.0008825349998460297,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13915284500012604,
"count": 1,
"self": 0.13915284500012604
}
}
}
}
}
}
}