Anasmob's picture
First Push
bd289b6
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7784309387207031,
"min": 0.7784309387207031,
"max": 2.862492561340332,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7432.45849609375,
"min": 7432.45849609375,
"max": 29314.78515625,
"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": 13.150735855102539,
"min": 0.3156082034111023,
"max": 13.150735855102539,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2564.3935546875,
"min": 61.227989196777344,
"max": 2644.34619140625,
"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": 0.0688459770527569,
"min": 0.062490396310193534,
"max": 0.0723013033287134,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2753839082110276,
"min": 0.24996158524077414,
"max": 0.361506516643567,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19597893817459838,
"min": 0.12351768716745189,
"max": 0.2832041992860682,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7839157526983935,
"min": 0.49407074866980755,
"max": 1.380737345183597,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000009e-06,
"min": 8.082097306000009e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.2328389224000035e-05,
"min": 3.2328389224000035e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269399999999998,
"min": 0.10269399999999998,
"max": 0.197294,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.4107759999999999,
"min": 0.4107759999999999,
"max": 0.9617200000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.004864970599999999,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.227272727272727,
"min": 3.590909090909091,
"max": 26.227272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1154.0,
"min": 158.0,
"max": 1425.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.227272727272727,
"min": 3.590909090909091,
"max": 26.227272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1154.0,
"min": 158.0,
"max": 1425.0,
"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": "1701369990",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1701370540"
},
"total": 549.658825722,
"count": 1,
"self": 0.4327204289999145,
"children": {
"run_training.setup": {
"total": 0.0801661340000237,
"count": 1,
"self": 0.0801661340000237
},
"TrainerController.start_learning": {
"total": 549.145939159,
"count": 1,
"self": 0.6085821169955352,
"children": {
"TrainerController._reset_env": {
"total": 3.3667839309999863,
"count": 1,
"self": 3.3667839309999863
},
"TrainerController.advance": {
"total": 545.0802445680046,
"count": 18199,
"self": 0.27485265700056516,
"children": {
"env_step": {
"total": 544.805391911004,
"count": 18199,
"self": 389.31621202800176,
"children": {
"SubprocessEnvManager._take_step": {
"total": 155.18405689900806,
"count": 18199,
"self": 1.4968271820158634,
"children": {
"TorchPolicy.evaluate": {
"total": 153.6872297169922,
"count": 18199,
"self": 153.6872297169922
}
}
},
"workers": {
"total": 0.30512298399418114,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 547.8227650990119,
"count": 18199,
"is_parallel": true,
"self": 297.56270731001587,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0030447019999542135,
"count": 1,
"is_parallel": true,
"self": 0.0008089589998689917,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002235743000085222,
"count": 10,
"is_parallel": true,
"self": 0.002235743000085222
}
}
},
"UnityEnvironment.step": {
"total": 0.056933071999992535,
"count": 1,
"is_parallel": true,
"self": 0.0006240579999712281,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003717410000376731,
"count": 1,
"is_parallel": true,
"self": 0.0003717410000376731
},
"communicator.exchange": {
"total": 0.053616465999994034,
"count": 1,
"is_parallel": true,
"self": 0.053616465999994034
},
"steps_from_proto": {
"total": 0.0023208069999895997,
"count": 1,
"is_parallel": true,
"self": 0.0004260109998313055,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018947960001582942,
"count": 10,
"is_parallel": true,
"self": 0.0018947960001582942
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 250.26005778899605,
"count": 18198,
"is_parallel": true,
"self": 10.790298495984075,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.5755942320003555,
"count": 18198,
"is_parallel": true,
"self": 5.5755942320003555
},
"communicator.exchange": {
"total": 198.349429874002,
"count": 18198,
"is_parallel": true,
"self": 198.349429874002
},
"steps_from_proto": {
"total": 35.54473518700962,
"count": 18198,
"is_parallel": true,
"self": 6.796368805047962,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.74836638196166,
"count": 181980,
"is_parallel": true,
"self": 28.74836638196166
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.8828000015200814e-05,
"count": 1,
"self": 3.8828000015200814e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 541.0224687579789,
"count": 498291,
"is_parallel": true,
"self": 11.311941500991225,
"children": {
"process_trajectory": {
"total": 272.4754054839882,
"count": 498291,
"is_parallel": true,
"self": 271.78954560198827,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6858598819999315,
"count": 4,
"is_parallel": true,
"self": 0.6858598819999315
}
}
},
"_update_policy": {
"total": 257.23512177299943,
"count": 90,
"is_parallel": true,
"self": 91.30305591199732,
"children": {
"TorchPPOOptimizer.update": {
"total": 165.93206586100212,
"count": 7645,
"is_parallel": true,
"self": 165.93206586100212
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09028971499992622,
"count": 1,
"self": 0.0009139079999158639,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08937580700001035,
"count": 1,
"self": 0.08937580700001035
}
}
}
}
}
}
}