MakiPan's picture
push first snowball attempt
14f9fb3
raw
history blame
18.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.2215951681137085,
"min": 1.2215951681137085,
"max": 2.794477939605713,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 11717.541015625,
"min": 11717.541015625,
"max": 28710.466796875,
"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": 10.461886405944824,
"min": 0.5010529160499573,
"max": 10.461886405944824,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2040.06787109375,
"min": 97.20426940917969,
"max": 2060.15771484375,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0699305470256613,
"min": 0.0699305470256613,
"max": 0.08960401106291387,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2797221881026452,
"min": 0.2797221881026452,
"max": 0.44802005531456934,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2556989218893589,
"min": 0.12977344808899158,
"max": 0.2745526036941538,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.0227956875574356,
"min": 0.5190937923559663,
"max": 1.3727630184707689,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 2.694009730600002e-05,
"min": 2.694009730600002e-05,
"max": 0.000972940002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.00010776038922400007,
"min": 0.00010776038922400007,
"max": 0.00461720003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.104041,
"min": 0.104041,
"max": 0.24594100000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.416164,
"min": 0.416164,
"max": 1.19258,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.004864970599999999,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828000000003,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 21.318181818181817,
"min": 3.7045454545454546,
"max": 21.318181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 938.0,
"min": 163.0,
"max": 1149.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 21.318181818181817,
"min": 3.7045454545454546,
"max": 21.318181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 938.0,
"min": 163.0,
"max": 1149.0,
"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": "1679338854",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1679339441"
},
"total": 587.296048915,
"count": 1,
"self": 0.38419044299996585,
"children": {
"run_training.setup": {
"total": 0.1896594190000087,
"count": 1,
"self": 0.1896594190000087
},
"TrainerController.start_learning": {
"total": 586.722199053,
"count": 1,
"self": 0.5503863369934834,
"children": {
"TrainerController._reset_env": {
"total": 8.036707009999986,
"count": 1,
"self": 8.036707009999986
},
"TrainerController.advance": {
"total": 577.8770210500066,
"count": 18213,
"self": 0.2837304000017866,
"children": {
"env_step": {
"total": 577.5932906500049,
"count": 18213,
"self": 431.6877708800008,
"children": {
"SubprocessEnvManager._take_step": {
"total": 145.62946310000507,
"count": 18213,
"self": 1.9768423899953405,
"children": {
"TorchPolicy.evaluate": {
"total": 143.65262071000973,
"count": 18213,
"self": 143.65262071000973
}
}
},
"workers": {
"total": 0.2760566699989795,
"count": 18213,
"self": 0.0,
"children": {
"worker_root": {
"total": 585.0207596749847,
"count": 18213,
"is_parallel": true,
"self": 346.1906275059896,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005414013999939016,
"count": 1,
"is_parallel": true,
"self": 0.0037184689996365705,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016955450003024453,
"count": 10,
"is_parallel": true,
"self": 0.0016955450003024453
}
}
},
"UnityEnvironment.step": {
"total": 0.03846317799991539,
"count": 1,
"is_parallel": true,
"self": 0.0006571399998165361,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004382170000098995,
"count": 1,
"is_parallel": true,
"self": 0.0004382170000098995
},
"communicator.exchange": {
"total": 0.03452606000007563,
"count": 1,
"is_parallel": true,
"self": 0.03452606000007563
},
"steps_from_proto": {
"total": 0.002841761000013321,
"count": 1,
"is_parallel": true,
"self": 0.0006253479999713818,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002216413000041939,
"count": 10,
"is_parallel": true,
"self": 0.002216413000041939
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 238.83013216899508,
"count": 18212,
"is_parallel": true,
"self": 9.744001692997813,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.334840603000657,
"count": 18212,
"is_parallel": true,
"self": 5.334840603000657
},
"communicator.exchange": {
"total": 191.29234942200344,
"count": 18212,
"is_parallel": true,
"self": 191.29234942200344
},
"steps_from_proto": {
"total": 32.45894045099317,
"count": 18212,
"is_parallel": true,
"self": 6.429052080985343,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.029888370007825,
"count": 182120,
"is_parallel": true,
"self": 26.029888370007825
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00010702899999159854,
"count": 1,
"self": 0.00010702899999159854,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 574.4113460240541,
"count": 387052,
"is_parallel": true,
"self": 9.966734134131912,
"children": {
"process_trajectory": {
"total": 277.0544231479221,
"count": 387052,
"is_parallel": true,
"self": 274.7680436429222,
"children": {
"RLTrainer._checkpoint": {
"total": 2.2863795049999,
"count": 4,
"is_parallel": true,
"self": 2.2863795049999
}
}
},
"_update_policy": {
"total": 287.3901887420001,
"count": 90,
"is_parallel": true,
"self": 116.35771260900628,
"children": {
"TorchPPOOptimizer.update": {
"total": 171.0324761329938,
"count": 9174,
"is_parallel": true,
"self": 171.0324761329938
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.25797762699994564,
"count": 1,
"self": 0.0023782389998814324,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2555993880000642,
"count": 1,
"self": 0.2555993880000642
}
}
}
}
}
}
}