2qbdp5's picture
First Push
d4c81fc verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.837575376033783,
"min": 0.837575376033783,
"max": 2.855473279953003,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7960.31640625,
"min": 7960.31640625,
"max": 29148.671875,
"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": 12.878758430480957,
"min": 0.4324301481246948,
"max": 12.878758430480957,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2511.35791015625,
"min": 83.89144897460938,
"max": 2590.74169921875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06694526492584355,
"min": 0.060286965670849325,
"max": 0.07510363736946601,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2677810597033742,
"min": 0.2411478626833973,
"max": 0.35716538593645536,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18883120962509922,
"min": 0.12425830431154691,
"max": 0.26882610937543944,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7553248385003969,
"min": 0.49703321724618765,
"max": 1.3123062837357615,
"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": 25.318181818181817,
"min": 3.25,
"max": 25.472727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1114.0,
"min": 143.0,
"max": 1401.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.318181818181817,
"min": 3.25,
"max": 25.472727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1114.0,
"min": 143.0,
"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": "1767441451",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1767441902"
},
"total": 451.193825544,
"count": 1,
"self": 0.4402970579999419,
"children": {
"run_training.setup": {
"total": 0.02680576000000201,
"count": 1,
"self": 0.02680576000000201
},
"TrainerController.start_learning": {
"total": 450.72672272600005,
"count": 1,
"self": 0.39261282498512173,
"children": {
"TrainerController._reset_env": {
"total": 2.7574517739999465,
"count": 1,
"self": 2.7574517739999465
},
"TrainerController.advance": {
"total": 447.5008859250147,
"count": 18192,
"self": 0.39875708298700374,
"children": {
"env_step": {
"total": 327.5829386960171,
"count": 18192,
"self": 257.1557873940501,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.19857671897034,
"count": 18192,
"self": 1.321449629979611,
"children": {
"TorchPolicy.evaluate": {
"total": 68.87712708899073,
"count": 18192,
"self": 68.87712708899073
}
}
},
"workers": {
"total": 0.22857458299665723,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 449.0236938590082,
"count": 18192,
"is_parallel": true,
"self": 223.24636309500454,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0046274830000356815,
"count": 1,
"is_parallel": true,
"self": 0.0032575220001263006,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001369960999909381,
"count": 10,
"is_parallel": true,
"self": 0.001369960999909381
}
}
},
"UnityEnvironment.step": {
"total": 0.03616278599997713,
"count": 1,
"is_parallel": true,
"self": 0.0005930710000257022,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040253899999243004,
"count": 1,
"is_parallel": true,
"self": 0.00040253899999243004
},
"communicator.exchange": {
"total": 0.033189472999993086,
"count": 1,
"is_parallel": true,
"self": 0.033189472999993086
},
"steps_from_proto": {
"total": 0.0019777029999659135,
"count": 1,
"is_parallel": true,
"self": 0.000355831999968359,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016218709999975545,
"count": 10,
"is_parallel": true,
"self": 0.0016218709999975545
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 225.77733076400364,
"count": 18191,
"is_parallel": true,
"self": 10.590137285997912,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.5557259019998355,
"count": 18191,
"is_parallel": true,
"self": 5.5557259019998355
},
"communicator.exchange": {
"total": 172.2047089129985,
"count": 18191,
"is_parallel": true,
"self": 172.2047089129985
},
"steps_from_proto": {
"total": 37.42675866300738,
"count": 18191,
"is_parallel": true,
"self": 6.6949911960214195,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.731767466985957,
"count": 181910,
"is_parallel": true,
"self": 30.731767466985957
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 119.5191901460106,
"count": 18192,
"self": 0.48788173901550635,
"children": {
"process_trajectory": {
"total": 26.839188268995485,
"count": 18192,
"self": 26.308235134995357,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5309531340001286,
"count": 4,
"self": 0.5309531340001286
}
}
},
"_update_policy": {
"total": 92.19212013799961,
"count": 90,
"self": 38.014182021000124,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.177938116999485,
"count": 4587,
"self": 54.177938116999485
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.950000847107731e-07,
"count": 1,
"self": 8.950000847107731e-07
},
"TrainerController._save_models": {
"total": 0.07577130700019552,
"count": 1,
"self": 0.0006758840002021316,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07509542299999339,
"count": 1,
"self": 0.07509542299999339
}
}
}
}
}
}
}