bayerasif's picture
First Push
386a5d3 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8004582524299622,
"min": 0.8004582524299622,
"max": 2.8632168769836426,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7607.55517578125,
"min": 7607.55517578125,
"max": 29227.71875,
"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": 12.881099700927734,
"min": 0.26382723450660706,
"max": 12.881099700927734,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2511.814453125,
"min": 51.1824836730957,
"max": 2608.515625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0692745111993966,
"min": 0.05924142605234759,
"max": 0.07540174294188226,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2770980447975864,
"min": 0.23696570420939037,
"max": 0.37076991310288365,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20698235381175492,
"min": 0.11945774100889797,
"max": 0.30456263155621643,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8279294152470197,
"min": 0.4778309640355919,
"max": 1.3766835001753828,
"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": 25.65909090909091,
"min": 3.4545454545454546,
"max": 25.65909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1129.0,
"min": 152.0,
"max": 1382.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.65909090909091,
"min": 3.4545454545454546,
"max": 25.65909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1129.0,
"min": 152.0,
"max": 1382.0,
"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": "1742205452",
"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",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1742205961"
},
"total": 509.27371135400006,
"count": 1,
"self": 0.4914800390000096,
"children": {
"run_training.setup": {
"total": 0.025650685000016438,
"count": 1,
"self": 0.025650685000016438
},
"TrainerController.start_learning": {
"total": 508.75658063000003,
"count": 1,
"self": 0.4544925570090186,
"children": {
"TrainerController._reset_env": {
"total": 3.5568356690000087,
"count": 1,
"self": 3.5568356690000087
},
"TrainerController.advance": {
"total": 504.6444247739911,
"count": 18192,
"self": 0.46685374299812565,
"children": {
"env_step": {
"total": 364.84889461500666,
"count": 18192,
"self": 276.8066851679995,
"children": {
"SubprocessEnvManager._take_step": {
"total": 87.77235958701237,
"count": 18192,
"self": 1.51648381901623,
"children": {
"TorchPolicy.evaluate": {
"total": 86.25587576799614,
"count": 18192,
"self": 86.25587576799614
}
}
},
"workers": {
"total": 0.2698498599947925,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 507.0184510979943,
"count": 18192,
"is_parallel": true,
"self": 265.54423990600094,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006243630000028588,
"count": 1,
"is_parallel": true,
"self": 0.004473354000083418,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00177027599994517,
"count": 10,
"is_parallel": true,
"self": 0.00177027599994517
}
}
},
"UnityEnvironment.step": {
"total": 0.0395177160000344,
"count": 1,
"is_parallel": true,
"self": 0.0007308280000302148,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004437399999801528,
"count": 1,
"is_parallel": true,
"self": 0.0004437399999801528
},
"communicator.exchange": {
"total": 0.03601450100001102,
"count": 1,
"is_parallel": true,
"self": 0.03601450100001102
},
"steps_from_proto": {
"total": 0.0023286470000130066,
"count": 1,
"is_parallel": true,
"self": 0.00043223499994837766,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001896412000064629,
"count": 10,
"is_parallel": true,
"self": 0.001896412000064629
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 241.47421119199333,
"count": 18191,
"is_parallel": true,
"self": 11.560055293994367,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.5611595780061975,
"count": 18191,
"is_parallel": true,
"self": 6.5611595780061975
},
"communicator.exchange": {
"total": 185.0797836929952,
"count": 18191,
"is_parallel": true,
"self": 185.0797836929952
},
"steps_from_proto": {
"total": 38.27321262699758,
"count": 18191,
"is_parallel": true,
"self": 7.001114175995383,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.272098451002194,
"count": 181910,
"is_parallel": true,
"self": 31.272098451002194
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 139.3286764159863,
"count": 18192,
"self": 0.5775916079891203,
"children": {
"process_trajectory": {
"total": 31.525484752997272,
"count": 18192,
"self": 31.0323035829972,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4931811700000708,
"count": 4,
"self": 0.4931811700000708
}
}
},
"_update_policy": {
"total": 107.22560005499992,
"count": 90,
"self": 43.26294323600149,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.962656818998425,
"count": 4587,
"self": 63.962656818998425
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0189999102294678e-06,
"count": 1,
"self": 1.0189999102294678e-06
},
"TrainerController._save_models": {
"total": 0.10082661100000223,
"count": 1,
"self": 0.000991221000049336,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0998353899999529,
"count": 1,
"self": 0.0998353899999529
}
}
}
}
}
}
}