MohanThota's picture
First Push
13000d7 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8527114987373352,
"min": 0.8527114987373352,
"max": 2.847898006439209,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8104.169921875,
"min": 8104.169921875,
"max": 29071.34375,
"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": 12.851581573486328,
"min": 0.40326422452926636,
"max": 12.851581573486328,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2506.058349609375,
"min": 78.23326110839844,
"max": 2578.81103515625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07474096430204928,
"min": 0.06376517352814429,
"max": 0.07542593929718029,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2989638572081971,
"min": 0.25561232567018605,
"max": 0.37712969648590144,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19288423094971507,
"min": 0.15366812300178972,
"max": 0.29291098725562004,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7715369237988603,
"min": 0.6146724920071589,
"max": 1.4645549362781,
"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": 25.295454545454547,
"min": 4.386363636363637,
"max": 25.4,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1113.0,
"min": 193.0,
"max": 1397.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.295454545454547,
"min": 4.386363636363637,
"max": 25.4,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1113.0,
"min": 193.0,
"max": 1397.0,
"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": "1754092489",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1754092901"
},
"total": 412.8633375410002,
"count": 1,
"self": 0.43753824800000984,
"children": {
"run_training.setup": {
"total": 0.0282141220000085,
"count": 1,
"self": 0.0282141220000085
},
"TrainerController.start_learning": {
"total": 412.3975851710002,
"count": 1,
"self": 0.3249662649830043,
"children": {
"TrainerController._reset_env": {
"total": 3.2929003659999125,
"count": 1,
"self": 3.2929003659999125
},
"TrainerController.advance": {
"total": 408.6986491650173,
"count": 18192,
"self": 0.34476217301516954,
"children": {
"env_step": {
"total": 291.7463208540098,
"count": 18192,
"self": 225.0247817570364,
"children": {
"SubprocessEnvManager._take_step": {
"total": 66.52998370799355,
"count": 18192,
"self": 1.2126500919794125,
"children": {
"TorchPolicy.evaluate": {
"total": 65.31733361601414,
"count": 18192,
"self": 65.31733361601414
}
}
},
"workers": {
"total": 0.19155538897985025,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 411.11657181800865,
"count": 18192,
"is_parallel": true,
"self": 212.7736542680309,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005298826000171175,
"count": 1,
"is_parallel": true,
"self": 0.004013828000324793,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012849979998463823,
"count": 10,
"is_parallel": true,
"self": 0.0012849979998463823
}
}
},
"UnityEnvironment.step": {
"total": 0.03497008900012588,
"count": 1,
"is_parallel": true,
"self": 0.0005439600001864164,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003841849998025282,
"count": 1,
"is_parallel": true,
"self": 0.0003841849998025282
},
"communicator.exchange": {
"total": 0.032251739000003,
"count": 1,
"is_parallel": true,
"self": 0.032251739000003
},
"steps_from_proto": {
"total": 0.0017902050001339376,
"count": 1,
"is_parallel": true,
"self": 0.00034722300006251317,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014429820000714244,
"count": 10,
"is_parallel": true,
"self": 0.0014429820000714244
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 198.34291754997776,
"count": 18191,
"is_parallel": true,
"self": 9.642955071995175,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.166401906009469,
"count": 18191,
"is_parallel": true,
"self": 5.166401906009469
},
"communicator.exchange": {
"total": 153.11249061299668,
"count": 18191,
"is_parallel": true,
"self": 153.11249061299668
},
"steps_from_proto": {
"total": 30.42106995897643,
"count": 18191,
"is_parallel": true,
"self": 5.2615742909740675,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.159495668002364,
"count": 181910,
"is_parallel": true,
"self": 25.159495668002364
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 116.60756613799231,
"count": 18192,
"self": 0.38249022999389126,
"children": {
"process_trajectory": {
"total": 25.638508904998844,
"count": 18192,
"self": 25.249496120998856,
"children": {
"RLTrainer._checkpoint": {
"total": 0.38901278399998773,
"count": 4,
"self": 0.38901278399998773
}
}
},
"_update_policy": {
"total": 90.58656700299957,
"count": 90,
"self": 37.416296876005845,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.17027012699373,
"count": 4587,
"self": 53.17027012699373
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0409999049443286e-06,
"count": 1,
"self": 1.0409999049443286e-06
},
"TrainerController._save_models": {
"total": 0.08106833400006508,
"count": 1,
"self": 0.00091435200010892,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08015398199995616,
"count": 1,
"self": 0.08015398199995616
}
}
}
}
}
}
}