KnoY's picture
First Push
7820ef9 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.701324462890625,
"min": 0.701324462890625,
"max": 2.859485626220703,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6665.3876953125,
"min": 6665.3876953125,
"max": 29189.62890625,
"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": 12.947745323181152,
"min": 0.337263286113739,
"max": 12.947745323181152,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2524.810302734375,
"min": 65.4290771484375,
"max": 2619.32568359375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07072912689239043,
"min": 0.060238727997941666,
"max": 0.07372874776346555,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2829165075695617,
"min": 0.24130083850753842,
"max": 0.3638037669486092,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17449279874563217,
"min": 0.10804914355656936,
"max": 0.281855143402137,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6979711949825287,
"min": 0.43219657422627744,
"max": 1.409275717010685,
"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": 25.386363636363637,
"min": 2.6818181818181817,
"max": 25.8,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1117.0,
"min": 118.0,
"max": 1419.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.386363636363637,
"min": 2.6818181818181817,
"max": 25.8,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1117.0,
"min": 118.0,
"max": 1419.0,
"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": "1766463085",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /kaggle/input/config1/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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1766463485"
},
"total": 400.07053461999976,
"count": 1,
"self": 0.32333276500003194,
"children": {
"run_training.setup": {
"total": 0.026161844999933237,
"count": 1,
"self": 0.026161844999933237
},
"TrainerController.start_learning": {
"total": 399.7210400099998,
"count": 1,
"self": 0.3385545689857281,
"children": {
"TrainerController._reset_env": {
"total": 2.062974786000268,
"count": 1,
"self": 2.062974786000268
},
"TrainerController.advance": {
"total": 397.2328420360136,
"count": 18192,
"self": 0.3706869770285266,
"children": {
"env_step": {
"total": 282.3009538379574,
"count": 18192,
"self": 211.74994313496018,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.33858798601386,
"count": 18192,
"self": 1.2453711540424592,
"children": {
"TorchPolicy.evaluate": {
"total": 69.0932168319714,
"count": 18192,
"self": 69.0932168319714
}
}
},
"workers": {
"total": 0.212422716983383,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 398.797743023003,
"count": 18192,
"is_parallel": true,
"self": 212.2467507510064,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002276652000091417,
"count": 1,
"is_parallel": true,
"self": 0.0006580940007552272,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016185579993361898,
"count": 10,
"is_parallel": true,
"self": 0.0016185579993361898
}
}
},
"UnityEnvironment.step": {
"total": 0.029713162000007287,
"count": 1,
"is_parallel": true,
"self": 0.0003922979999515519,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000251281000146264,
"count": 1,
"is_parallel": true,
"self": 0.000251281000146264
},
"communicator.exchange": {
"total": 0.02767869299987069,
"count": 1,
"is_parallel": true,
"self": 0.02767869299987069
},
"steps_from_proto": {
"total": 0.0013908900000387803,
"count": 1,
"is_parallel": true,
"self": 0.0003138299994134286,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010770600006253517,
"count": 10,
"is_parallel": true,
"self": 0.0010770600006253517
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 186.55099227199662,
"count": 18191,
"is_parallel": true,
"self": 7.529676282989385,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.10229266099077,
"count": 18191,
"is_parallel": true,
"self": 4.10229266099077
},
"communicator.exchange": {
"total": 150.73801396702765,
"count": 18191,
"is_parallel": true,
"self": 150.73801396702765
},
"steps_from_proto": {
"total": 24.18100936098881,
"count": 18191,
"is_parallel": true,
"self": 4.416292834023352,
"children": {
"_process_rank_one_or_two_observation": {
"total": 19.764716526965458,
"count": 181910,
"is_parallel": true,
"self": 19.764716526965458
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 114.56120122102766,
"count": 18192,
"self": 0.40431972203032274,
"children": {
"process_trajectory": {
"total": 26.042061476999606,
"count": 18192,
"self": 25.55481587099939,
"children": {
"RLTrainer._checkpoint": {
"total": 0.48724560600021505,
"count": 4,
"self": 0.48724560600021505
}
}
},
"_update_policy": {
"total": 88.11482002199773,
"count": 90,
"self": 34.48180055900866,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.63301946298907,
"count": 4587,
"self": 53.63301946298907
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0439998732181266e-06,
"count": 1,
"self": 1.0439998732181266e-06
},
"TrainerController._save_models": {
"total": 0.08666757500031963,
"count": 1,
"self": 0.001037775000440888,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08562979999987874,
"count": 1,
"self": 0.08562979999987874
}
}
}
}
}
}
}