tcottone's picture
First Push
57c86a6 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8271796107292175,
"min": 0.8271796107292175,
"max": 2.8674070835113525,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7961.603515625,
"min": 7961.603515625,
"max": 29333.57421875,
"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": 12.825800895690918,
"min": 0.2550135850906372,
"max": 12.825800895690918,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2501.03125,
"min": 49.47263717651367,
"max": 2585.90087890625,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07401933609478019,
"min": 0.06442176615020762,
"max": 0.0747462403555355,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29607734437912075,
"min": 0.25768706460083046,
"max": 0.3694393268595769,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19492375605977047,
"min": 0.1134301907800631,
"max": 0.2944222167134285,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7796950242390819,
"min": 0.4537207631202524,
"max": 1.3685771726510105,
"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": 25.772727272727273,
"min": 3.1363636363636362,
"max": 25.772727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1134.0,
"min": 138.0,
"max": 1396.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.772727272727273,
"min": 3.1363636363636362,
"max": 25.772727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1134.0,
"min": 138.0,
"max": 1396.0,
"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": "1722239106",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1722239576"
},
"total": 470.3994039979999,
"count": 1,
"self": 0.6977898129998721,
"children": {
"run_training.setup": {
"total": 0.061851199999978235,
"count": 1,
"self": 0.061851199999978235
},
"TrainerController.start_learning": {
"total": 469.63976298500006,
"count": 1,
"self": 0.5941051069978585,
"children": {
"TrainerController._reset_env": {
"total": 3.092803789999948,
"count": 1,
"self": 3.092803789999948
},
"TrainerController.advance": {
"total": 465.7931410290024,
"count": 18216,
"self": 0.2825741709966678,
"children": {
"env_step": {
"total": 465.51056685800575,
"count": 18216,
"self": 301.6454908900024,
"children": {
"SubprocessEnvManager._take_step": {
"total": 163.5688184940011,
"count": 18216,
"self": 1.529747794987884,
"children": {
"TorchPolicy.evaluate": {
"total": 162.03907069901322,
"count": 18216,
"self": 162.03907069901322
}
}
},
"workers": {
"total": 0.2962574740022319,
"count": 18216,
"self": 0.0,
"children": {
"worker_root": {
"total": 468.1992790460066,
"count": 18216,
"is_parallel": true,
"self": 238.34856306700715,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005839611000055811,
"count": 1,
"is_parallel": true,
"self": 0.004014394000137145,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018252169999186663,
"count": 10,
"is_parallel": true,
"self": 0.0018252169999186663
}
}
},
"UnityEnvironment.step": {
"total": 0.03603613799998584,
"count": 1,
"is_parallel": true,
"self": 0.0007197569999561892,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003802300000188552,
"count": 1,
"is_parallel": true,
"self": 0.0003802300000188552
},
"communicator.exchange": {
"total": 0.03285260500001641,
"count": 1,
"is_parallel": true,
"self": 0.03285260500001641
},
"steps_from_proto": {
"total": 0.002083545999994385,
"count": 1,
"is_parallel": true,
"self": 0.00041471499991985183,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016688310000745332,
"count": 10,
"is_parallel": true,
"self": 0.0016688310000745332
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 229.85071597899946,
"count": 18215,
"is_parallel": true,
"self": 10.291373226009455,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.605053042001714,
"count": 18215,
"is_parallel": true,
"self": 5.605053042001714
},
"communicator.exchange": {
"total": 178.82160496199992,
"count": 18215,
"is_parallel": true,
"self": 178.82160496199992
},
"steps_from_proto": {
"total": 35.13268474898837,
"count": 18215,
"is_parallel": true,
"self": 6.7181818270272515,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.414502921961116,
"count": 182150,
"is_parallel": true,
"self": 28.414502921961116
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00017920499999490858,
"count": 1,
"self": 0.00017920499999490858,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 459.9584313930235,
"count": 681455,
"is_parallel": true,
"self": 14.973402154047903,
"children": {
"process_trajectory": {
"total": 253.7312759099749,
"count": 681455,
"is_parallel": true,
"self": 252.51680575397484,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2144701560000613,
"count": 4,
"is_parallel": true,
"self": 1.2144701560000613
}
}
},
"_update_policy": {
"total": 191.2537533290007,
"count": 90,
"is_parallel": true,
"self": 59.68628188999867,
"children": {
"TorchPPOOptimizer.update": {
"total": 131.56747143900202,
"count": 4587,
"is_parallel": true,
"self": 131.56747143900202
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15953385399984654,
"count": 1,
"self": 0.0012703169998076191,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15826353700003892,
"count": 1,
"self": 0.15826353700003892
}
}
}
}
}
}
}