benjipeng's picture
First Push
ed9d46a
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9874294996261597,
"min": 0.9864434599876404,
"max": 2.8660902976989746,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9438.8388671875,
"min": 9438.8388671875,
"max": 29414.68359375,
"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": 12.95145320892334,
"min": 0.4696316719055176,
"max": 12.95145320892334,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2525.533447265625,
"min": 91.1085433959961,
"max": 2627.650146484375,
"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": 0.06134362781948784,
"min": 0.06016000449948051,
"max": 0.0738981646398886,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24537451127795137,
"min": 0.24064001799792203,
"max": 0.369490823199443,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1986842172987321,
"min": 0.1131561124313842,
"max": 0.2678477030028315,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7947368691949284,
"min": 0.4526244497255368,
"max": 1.3357753321236254,
"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": 25.522727272727273,
"min": 3.3863636363636362,
"max": 25.545454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1123.0,
"min": 149.0,
"max": 1401.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.522727272727273,
"min": 3.3863636363636362,
"max": 25.545454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1123.0,
"min": 149.0,
"max": 1401.0,
"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": "1698678164",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1698678631"
},
"total": 466.835806543,
"count": 1,
"self": 0.4348714509999354,
"children": {
"run_training.setup": {
"total": 0.050726401000019905,
"count": 1,
"self": 0.050726401000019905
},
"TrainerController.start_learning": {
"total": 466.35020869100003,
"count": 1,
"self": 0.5402901169934466,
"children": {
"TrainerController._reset_env": {
"total": 8.738381844999935,
"count": 1,
"self": 8.738381844999935
},
"TrainerController.advance": {
"total": 456.9652453220066,
"count": 18209,
"self": 0.27081760700059476,
"children": {
"env_step": {
"total": 456.694427715006,
"count": 18209,
"self": 312.71139058900474,
"children": {
"SubprocessEnvManager._take_step": {
"total": 143.71016021801427,
"count": 18209,
"self": 1.4310174720120585,
"children": {
"TorchPolicy.evaluate": {
"total": 142.2791427460022,
"count": 18209,
"self": 142.2791427460022
}
}
},
"workers": {
"total": 0.2728769079869835,
"count": 18209,
"self": 0.0,
"children": {
"worker_root": {
"total": 465.09317635400214,
"count": 18209,
"is_parallel": true,
"self": 228.33782264699244,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006524795000018457,
"count": 1,
"is_parallel": true,
"self": 0.005107078000037291,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014177169999811667,
"count": 10,
"is_parallel": true,
"self": 0.0014177169999811667
}
}
},
"UnityEnvironment.step": {
"total": 0.03530777899993609,
"count": 1,
"is_parallel": true,
"self": 0.0006578210000043327,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040109600001869694,
"count": 1,
"is_parallel": true,
"self": 0.00040109600001869694
},
"communicator.exchange": {
"total": 0.03237446399998589,
"count": 1,
"is_parallel": true,
"self": 0.03237446399998589
},
"steps_from_proto": {
"total": 0.0018743979999271687,
"count": 1,
"is_parallel": true,
"self": 0.0003635439998106449,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015108540001165238,
"count": 10,
"is_parallel": true,
"self": 0.0015108540001165238
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 236.7553537070097,
"count": 18208,
"is_parallel": true,
"self": 10.536849481015224,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.341214750996301,
"count": 18208,
"is_parallel": true,
"self": 5.341214750996301
},
"communicator.exchange": {
"total": 187.5071931839974,
"count": 18208,
"is_parallel": true,
"self": 187.5071931839974
},
"steps_from_proto": {
"total": 33.37009629100078,
"count": 18208,
"is_parallel": true,
"self": 6.145093372022984,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.225002918977793,
"count": 182080,
"is_parallel": true,
"self": 27.225002918977793
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001310520001425175,
"count": 1,
"self": 0.0001310520001425175,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 453.17904144998545,
"count": 473503,
"is_parallel": true,
"self": 10.082571375881457,
"children": {
"process_trajectory": {
"total": 253.70076270610366,
"count": 473503,
"is_parallel": true,
"self": 252.62931688710364,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0714458190000187,
"count": 4,
"is_parallel": true,
"self": 1.0714458190000187
}
}
},
"_update_policy": {
"total": 189.39570736800033,
"count": 90,
"is_parallel": true,
"self": 58.38856233899628,
"children": {
"TorchPPOOptimizer.update": {
"total": 131.00714502900405,
"count": 4584,
"is_parallel": true,
"self": 131.00714502900405
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10616035499992904,
"count": 1,
"self": 0.0008963939999375725,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10526396099999147,
"count": 1,
"self": 0.10526396099999147
}
}
}
}
}
}
}