1aurent's picture
Wow such model
6081c8c
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0059523582458496,
"min": 1.0059523582458496,
"max": 2.862372398376465,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9604.8330078125,
"min": 9604.8330078125,
"max": 29345.04296875,
"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": 12.947747230529785,
"min": 0.4881535470485687,
"max": 12.947747230529785,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2524.810791015625,
"min": 94.70178985595703,
"max": 2619.18701171875,
"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.Losses.PolicyLoss.mean": {
"value": 0.07651351166115253,
"min": 0.0611253359853061,
"max": 0.07651822303869624,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3060540466446101,
"min": 0.2445013439412244,
"max": 0.35797665751762864,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21261401963876742,
"min": 0.1378776346134734,
"max": 0.2759649921281665,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8504560785550697,
"min": 0.5515105384538936,
"max": 1.3798249606408326,
"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.CumulativeReward.mean": {
"value": 25.272727272727273,
"min": 3.590909090909091,
"max": 25.818181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1112.0,
"min": 158.0,
"max": 1420.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.272727272727273,
"min": 3.590909090909091,
"max": 25.818181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1112.0,
"min": 158.0,
"max": 1420.0,
"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": "1689088441",
"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": "1689088951"
},
"total": 510.59043148199993,
"count": 1,
"self": 0.4401611819998834,
"children": {
"run_training.setup": {
"total": 0.04179937899999686,
"count": 1,
"self": 0.04179937899999686
},
"TrainerController.start_learning": {
"total": 510.10847092100005,
"count": 1,
"self": 0.5887725059870945,
"children": {
"TrainerController._reset_env": {
"total": 4.012834349000002,
"count": 1,
"self": 4.012834349000002
},
"TrainerController.advance": {
"total": 505.35678285301304,
"count": 18202,
"self": 0.3194896310113222,
"children": {
"env_step": {
"total": 505.0372932220017,
"count": 18202,
"self": 368.1075493169963,
"children": {
"SubprocessEnvManager._take_step": {
"total": 136.61837667300085,
"count": 18202,
"self": 1.945382368008552,
"children": {
"TorchPolicy.evaluate": {
"total": 134.6729943049923,
"count": 18202,
"self": 134.6729943049923
}
}
},
"workers": {
"total": 0.3113672320045566,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 508.40163646500383,
"count": 18202,
"is_parallel": true,
"self": 237.26137605099677,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007115802999976495,
"count": 1,
"is_parallel": true,
"self": 0.00409784400000035,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0030179589999761447,
"count": 10,
"is_parallel": true,
"self": 0.0030179589999761447
}
}
},
"UnityEnvironment.step": {
"total": 0.03678012399996078,
"count": 1,
"is_parallel": true,
"self": 0.0006773759999987305,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003272349999861035,
"count": 1,
"is_parallel": true,
"self": 0.0003272349999861035
},
"communicator.exchange": {
"total": 0.033426022000014655,
"count": 1,
"is_parallel": true,
"self": 0.033426022000014655
},
"steps_from_proto": {
"total": 0.00234949099996129,
"count": 1,
"is_parallel": true,
"self": 0.0003931119998696886,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019563790000916015,
"count": 10,
"is_parallel": true,
"self": 0.0019563790000916015
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 271.14026041400706,
"count": 18201,
"is_parallel": true,
"self": 11.324508839027828,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.771244048996039,
"count": 18201,
"is_parallel": true,
"self": 5.771244048996039
},
"communicator.exchange": {
"total": 214.07627587399622,
"count": 18201,
"is_parallel": true,
"self": 214.07627587399622
},
"steps_from_proto": {
"total": 39.96823165198697,
"count": 18201,
"is_parallel": true,
"self": 7.3610505649677975,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.60718108701917,
"count": 182010,
"is_parallel": true,
"self": 32.60718108701917
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012634999995952967,
"count": 1,
"self": 0.00012634999995952967,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 501.20337598196346,
"count": 490569,
"is_parallel": true,
"self": 11.157440960988026,
"children": {
"process_trajectory": {
"total": 277.1932761149751,
"count": 490569,
"is_parallel": true,
"self": 276.34610679697505,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8471693180000557,
"count": 4,
"is_parallel": true,
"self": 0.8471693180000557
}
}
},
"_update_policy": {
"total": 212.85265890600033,
"count": 90,
"is_parallel": true,
"self": 83.99415169899908,
"children": {
"TorchPPOOptimizer.update": {
"total": 128.85850720700125,
"count": 4587,
"is_parallel": true,
"self": 128.85850720700125
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1499548629999481,
"count": 1,
"self": 0.0008654779999233142,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14908938500002478,
"count": 1,
"self": 0.14908938500002478
}
}
}
}
}
}
}