lucasbertola's picture
First Push
564af5a
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9903756976127625,
"min": 0.9903756976127625,
"max": 2.8592560291290283,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9477.8955078125,
"min": 9477.8955078125,
"max": 29313.09375,
"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": 13.15394401550293,
"min": 0.26751744747161865,
"max": 13.15394401550293,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2565.01904296875,
"min": 51.89838409423828,
"max": 2661.2216796875,
"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": 0.06507496726493736,
"min": 0.06331819519688783,
"max": 0.08082611775094205,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26029986905974944,
"min": 0.25998697927513836,
"max": 0.40413058875471025,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21248235999076975,
"min": 0.12080448553737654,
"max": 0.28162610892425566,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.849929439963079,
"min": 0.48321794214950614,
"max": 1.4081305446212784,
"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": 25.75,
"min": 3.522727272727273,
"max": 25.8,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1133.0,
"min": 155.0,
"max": 1419.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.75,
"min": 3.522727272727273,
"max": 25.8,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1133.0,
"min": 155.0,
"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": "1689515942",
"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": "1689516414"
},
"total": 471.43790634699997,
"count": 1,
"self": 0.44071251500008657,
"children": {
"run_training.setup": {
"total": 0.04328695999993215,
"count": 1,
"self": 0.04328695999993215
},
"TrainerController.start_learning": {
"total": 470.95390687199995,
"count": 1,
"self": 0.6222185590061144,
"children": {
"TrainerController._reset_env": {
"total": 4.320406066000032,
"count": 1,
"self": 4.320406066000032
},
"TrainerController.advance": {
"total": 465.873773967994,
"count": 18202,
"self": 0.27509184699772504,
"children": {
"env_step": {
"total": 465.5986821209963,
"count": 18202,
"self": 338.4307023720004,
"children": {
"SubprocessEnvManager._take_step": {
"total": 126.88669091999827,
"count": 18202,
"self": 1.7892802950138957,
"children": {
"TorchPolicy.evaluate": {
"total": 125.09741062498438,
"count": 18202,
"self": 125.09741062498438
}
}
},
"workers": {
"total": 0.2812888289976172,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 469.4247224919976,
"count": 18202,
"is_parallel": true,
"self": 218.4036515419931,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005715071000054195,
"count": 1,
"is_parallel": true,
"self": 0.0042916450001939666,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014234259998602283,
"count": 10,
"is_parallel": true,
"self": 0.0014234259998602283
}
}
},
"UnityEnvironment.step": {
"total": 0.036128884000049766,
"count": 1,
"is_parallel": true,
"self": 0.00041919900013454026,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003363859999581109,
"count": 1,
"is_parallel": true,
"self": 0.0003363859999581109
},
"communicator.exchange": {
"total": 0.033541180000042914,
"count": 1,
"is_parallel": true,
"self": 0.033541180000042914
},
"steps_from_proto": {
"total": 0.0018321189999142007,
"count": 1,
"is_parallel": true,
"self": 0.0004346169997688776,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013975020001453231,
"count": 10,
"is_parallel": true,
"self": 0.0013975020001453231
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 251.0210709500045,
"count": 18201,
"is_parallel": true,
"self": 10.43886048201307,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.2594425450034805,
"count": 18201,
"is_parallel": true,
"self": 5.2594425450034805
},
"communicator.exchange": {
"total": 199.93329880599765,
"count": 18201,
"is_parallel": true,
"self": 199.93329880599765
},
"steps_from_proto": {
"total": 35.38946911699031,
"count": 18201,
"is_parallel": true,
"self": 6.397660915017241,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.991808201973072,
"count": 182010,
"is_parallel": true,
"self": 28.991808201973072
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014198700000633835,
"count": 1,
"self": 0.00014198700000633835,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 462.47679895907004,
"count": 459417,
"is_parallel": true,
"self": 9.598264279982914,
"children": {
"process_trajectory": {
"total": 255.62063704108687,
"count": 459417,
"is_parallel": true,
"self": 254.4772559930866,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1433810480002649,
"count": 4,
"is_parallel": true,
"self": 1.1433810480002649
}
}
},
"_update_policy": {
"total": 197.25789763800026,
"count": 90,
"is_parallel": true,
"self": 74.31024522200016,
"children": {
"TorchPPOOptimizer.update": {
"total": 122.9476524160001,
"count": 4584,
"is_parallel": true,
"self": 122.9476524160001
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13736629199979689,
"count": 1,
"self": 0.0009662189997925452,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13640007300000434,
"count": 1,
"self": 0.13640007300000434
}
}
}
}
}
}
}