{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9633113741874695, "min": 0.9633113741874695, "max": 2.851409435272217, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9155.3115234375, "min": 9155.3115234375, "max": 29107.1875, "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": 12.79420280456543, "min": 0.22075676918029785, "max": 12.79420280456543, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2494.86962890625, "min": 42.826812744140625, "max": 2598.6650390625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06850921050599758, "min": 0.06316236126186399, "max": 0.07816601845586453, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2740368420239903, "min": 0.25938708798425714, "max": 0.37477690193062535, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20521151398619017, "min": 0.10816038189930659, "max": 0.27734548215772586, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8208460559447607, "min": 0.43264152759722635, "max": 1.3867274107886294, "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": 25.045454545454547, "min": 2.9318181818181817, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1102.0, "min": 129.0, "max": 1380.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.045454545454547, "min": 2.9318181818181817, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1102.0, "min": 129.0, "max": 1380.0, "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": "1759390291", "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": "1759390725" }, "total": 434.05610544700016, "count": 1, "self": 0.43412453500013726, "children": { "run_training.setup": { "total": 0.02657160900002964, "count": 1, "self": 0.02657160900002964 }, "TrainerController.start_learning": { "total": 433.595409303, "count": 1, "self": 0.3581709300003695, "children": { "TrainerController._reset_env": { "total": 2.9988007800000105, "count": 1, "self": 2.9988007800000105 }, "TrainerController.advance": { "total": 430.1637390709998, "count": 18192, "self": 0.36588231599967, "children": { "env_step": { "total": 311.00691469700405, "count": 18192, "self": 244.08827143395865, "children": { "SubprocessEnvManager._take_step": { "total": 66.6992379670271, "count": 18192, "self": 1.2185897520359958, "children": { "TorchPolicy.evaluate": { "total": 65.4806482149911, "count": 18192, "self": 65.4806482149911 } } }, "workers": { "total": 0.2194052960182944, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 431.7137147989995, "count": 18192, "is_parallel": true, "self": 217.22681431299202, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005314559999987978, "count": 1, "is_parallel": true, "self": 0.004021056999818029, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012935030001699488, "count": 10, "is_parallel": true, "self": 0.0012935030001699488 } } }, "UnityEnvironment.step": { "total": 0.03441158999999061, "count": 1, "is_parallel": true, "self": 0.0005575479999606614, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041521600019223115, "count": 1, "is_parallel": true, "self": 0.00041521600019223115 }, "communicator.exchange": { "total": 0.03164804399989407, "count": 1, "is_parallel": true, "self": 0.03164804399989407 }, "steps_from_proto": { "total": 0.001790781999943647, "count": 1, "is_parallel": true, "self": 0.00032984600011332077, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014609359998303262, "count": 10, "is_parallel": true, "self": 0.0014609359998303262 } } } } } } }, "UnityEnvironment.step": { "total": 214.48690048600747, "count": 18191, "is_parallel": true, "self": 9.855487420965346, "children": { "UnityEnvironment._generate_step_input": { "total": 5.165339931009157, "count": 18191, "is_parallel": true, "self": 5.165339931009157 }, "communicator.exchange": { "total": 164.38909878001027, "count": 18191, "is_parallel": true, "self": 164.38909878001027 }, "steps_from_proto": { "total": 35.076974354022695, "count": 18191, "is_parallel": true, "self": 6.503351632058411, "children": { "_process_rank_one_or_two_observation": { "total": 28.573622721964284, "count": 181910, "is_parallel": true, "self": 28.573622721964284 } } } } } } } } } } }, "trainer_advance": { "total": 118.79094205799606, "count": 18192, "self": 0.47901103400681677, "children": { "process_trajectory": { "total": 26.16409001499028, "count": 18192, "self": 25.775989686990442, "children": { "RLTrainer._checkpoint": { "total": 0.38810032799983674, "count": 4, "self": 0.38810032799983674 } } }, "_update_policy": { "total": 92.14784100899897, "count": 90, "self": 37.981316270995876, "children": { "TorchPPOOptimizer.update": { "total": 54.16652473800309, "count": 4587, "self": 54.16652473800309 } } } } } } }, "trainer_threads": { "total": 8.239999260695186e-07, "count": 1, "self": 8.239999260695186e-07 }, "TrainerController._save_models": { "total": 0.074697697999909, "count": 1, "self": 0.0007264400001076865, "children": { "RLTrainer._checkpoint": { "total": 0.07397125799980131, "count": 1, "self": 0.07397125799980131 } } } } } } }