RAWsi-18's picture
First Push
7442c17 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9387471675872803,
"min": 0.9212210178375244,
"max": 2.8672304153442383,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9025.115234375,
"min": 9025.115234375,
"max": 29489.46484375,
"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": 12.824334144592285,
"min": 0.39173150062561035,
"max": 12.824334144592285,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2500.7451171875,
"min": 75.99591064453125,
"max": 2610.6201171875,
"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": 0.06807147768695894,
"min": 0.06340846372676975,
"max": 0.07506629889360952,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27228591074783576,
"min": 0.2549859455179745,
"max": 0.36454527843492474,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2073683795683524,
"min": 0.11570808273516413,
"max": 0.2852107124293552,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8294735182734096,
"min": 0.4628323309406565,
"max": 1.3678506457922506,
"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": 24.931818181818183,
"min": 3.6363636363636362,
"max": 25.436363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1097.0,
"min": 160.0,
"max": 1399.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.931818181818183,
"min": 3.6363636363636362,
"max": 25.436363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1097.0,
"min": 160.0,
"max": 1399.0,
"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": "1720928701",
"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": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1720929367"
},
"total": 665.8631706230001,
"count": 1,
"self": 0.5981226230001084,
"children": {
"run_training.setup": {
"total": 0.07664316500000723,
"count": 1,
"self": 0.07664316500000723
},
"TrainerController.start_learning": {
"total": 665.188404835,
"count": 1,
"self": 1.3247049630047059,
"children": {
"TrainerController._reset_env": {
"total": 3.957706900000005,
"count": 1,
"self": 3.957706900000005
},
"TrainerController.advance": {
"total": 659.8011015909952,
"count": 18221,
"self": 0.46972508399198887,
"children": {
"env_step": {
"total": 659.3313765070033,
"count": 18221,
"self": 508.0149107060133,
"children": {
"SubprocessEnvManager._take_step": {
"total": 150.85564829798898,
"count": 18221,
"self": 3.0093157019812793,
"children": {
"TorchPolicy.evaluate": {
"total": 147.8463325960077,
"count": 18221,
"self": 147.8463325960077
}
}
},
"workers": {
"total": 0.46081750300095337,
"count": 18221,
"self": 0.0,
"children": {
"worker_root": {
"total": 662.5543487319914,
"count": 18221,
"is_parallel": true,
"self": 314.1294488929919,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.010119637000002513,
"count": 1,
"is_parallel": true,
"self": 0.004753484000048047,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0053661529999544655,
"count": 10,
"is_parallel": true,
"self": 0.0053661529999544655
}
}
},
"UnityEnvironment.step": {
"total": 0.05202028799999425,
"count": 1,
"is_parallel": true,
"self": 0.0011061550000590614,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005464070000016363,
"count": 1,
"is_parallel": true,
"self": 0.0005464070000016363
},
"communicator.exchange": {
"total": 0.047270214999969085,
"count": 1,
"is_parallel": true,
"self": 0.047270214999969085
},
"steps_from_proto": {
"total": 0.00309751099996447,
"count": 1,
"is_parallel": true,
"self": 0.0006192950000354358,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0024782159999290343,
"count": 10,
"is_parallel": true,
"self": 0.0024782159999290343
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 348.42489983899947,
"count": 18220,
"is_parallel": true,
"self": 16.435906567996938,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.058868768001105,
"count": 18220,
"is_parallel": true,
"self": 8.058868768001105
},
"communicator.exchange": {
"total": 276.002330164,
"count": 18220,
"is_parallel": true,
"self": 276.002330164
},
"steps_from_proto": {
"total": 47.92779433900142,
"count": 18220,
"is_parallel": true,
"self": 9.695537653006795,
"children": {
"_process_rank_one_or_two_observation": {
"total": 38.23225668599463,
"count": 182200,
"is_parallel": true,
"self": 38.23225668599463
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00022794300002715318,
"count": 1,
"self": 0.00022794300002715318,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 652.4678362560599,
"count": 797550,
"is_parallel": true,
"self": 20.334076866069495,
"children": {
"process_trajectory": {
"total": 361.2402249239901,
"count": 797550,
"is_parallel": true,
"self": 359.6055902209902,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6346347029999038,
"count": 4,
"is_parallel": true,
"self": 1.6346347029999038
}
}
},
"_update_policy": {
"total": 270.89353446600023,
"count": 90,
"is_parallel": true,
"self": 75.90990977599472,
"children": {
"TorchPPOOptimizer.update": {
"total": 194.9836246900055,
"count": 4587,
"is_parallel": true,
"self": 194.9836246900055
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10466343799998867,
"count": 1,
"self": 0.0013529109999126376,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10331052700007604,
"count": 1,
"self": 0.10331052700007604
}
}
}
}
}
}
}