{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.002143383026123, "min": 1.002143383026123, "max": 2.8694119453430176, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9623.5830078125, "min": 9623.5830078125, "max": 29511.90234375, "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": 12.56418228149414, "min": 0.32530006766319275, "max": 12.56418228149414, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2450.015625, "min": 63.10821533203125, "max": 2518.0478515625, "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": 0.06578948340657186, "min": 0.061012868139739884, "max": 0.07526436924401386, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2631579336262874, "min": 0.24405147255895954, "max": 0.3730850697508739, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1957122599158217, "min": 0.10599944498230174, "max": 0.29366141849873106, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7828490396632868, "min": 0.42399777992920695, "max": 1.4683070924936554, "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": 2.727272727272727, "max": 24.931818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1097.0, "min": 120.0, "max": 1368.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.931818181818183, "min": 2.727272727272727, "max": 24.931818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1097.0, "min": 120.0, "max": 1368.0, "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": "1729576612", "python_version": "3.10.12 (main, Jun 12 2024, 02:25:10) [GCC 12.2.0]", "command_line_arguments": "/home/luser/.pyenv/versions/3.10.12/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": "2.4.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1729576930" }, "total": 317.8528209384531, "count": 1, "self": 0.2201411183923483, "children": { "run_training.setup": { "total": 0.1493026465177536, "count": 1, "self": 0.1493026465177536 }, "TrainerController.start_learning": { "total": 317.483377173543, "count": 1, "self": 0.4942772537469864, "children": { "TrainerController._reset_env": { "total": 1.2777200918644667, "count": 1, "self": 1.2777200918644667 }, "TrainerController.advance": { "total": 315.65588099882007, "count": 18208, "self": 0.24032771959900856, "children": { "env_step": { "total": 315.41555327922106, "count": 18208, "self": 231.51014351658523, "children": { "SubprocessEnvManager._take_step": { "total": 83.67387328110635, "count": 18208, "self": 1.1666073575615883, "children": { "TorchPolicy.evaluate": { "total": 82.50726592354476, "count": 18208, "self": 82.50726592354476 } } }, "workers": { "total": 0.23153648152947426, "count": 18208, "self": 0.0, "children": { "worker_root": { "total": 316.96725662238896, "count": 18208, "is_parallel": true, "self": 172.4194098226726, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0015680287033319473, "count": 1, "is_parallel": true, "self": 0.000452972948551178, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011150557547807693, "count": 10, "is_parallel": true, "self": 0.0011150557547807693 } } }, "UnityEnvironment.step": { "total": 0.024469077587127686, "count": 1, "is_parallel": true, "self": 0.0003335755318403244, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023067928850650787, "count": 1, "is_parallel": true, "self": 0.00023067928850650787 }, "communicator.exchange": { "total": 0.022788627073168755, "count": 1, "is_parallel": true, "self": 0.022788627073168755 }, "steps_from_proto": { "total": 0.0011161956936120987, "count": 1, "is_parallel": true, "self": 0.0002922993153333664, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008238963782787323, "count": 10, "is_parallel": true, "self": 0.0008238963782787323 } } } } } } }, "UnityEnvironment.step": { "total": 144.54784679971635, "count": 18207, "is_parallel": true, "self": 6.313228230923414, "children": { "UnityEnvironment._generate_step_input": { "total": 4.166642235592008, "count": 18207, "is_parallel": true, "self": 4.166642235592008 }, "communicator.exchange": { "total": 112.24370483122766, "count": 18207, "is_parallel": true, "self": 112.24370483122766 }, "steps_from_proto": { "total": 21.82427150197327, "count": 18207, "is_parallel": true, "self": 4.9589143972843885, "children": { "_process_rank_one_or_two_observation": { "total": 16.865357104688883, "count": 182070, "is_parallel": true, "self": 16.865357104688883 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00019265525043010712, "count": 1, "self": 0.00019265525043010712, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 315.1159566491842, "count": 150643, "is_parallel": true, "self": 2.5816312804818153, "children": { "process_trajectory": { "total": 170.72974267043173, "count": 150643, "is_parallel": true, "self": 170.22571489028633, "children": { "RLTrainer._checkpoint": { "total": 0.5040277801454067, "count": 4, "is_parallel": true, "self": 0.5040277801454067 } } }, "_update_policy": { "total": 141.80458269827068, "count": 90, "is_parallel": true, "self": 38.252048183232546, "children": { "TorchPPOOptimizer.update": { "total": 103.55253451503813, "count": 4587, "is_parallel": true, "self": 103.55253451503813 } } } } } } } } }, "TrainerController._save_models": { "total": 0.055306173861026764, "count": 1, "self": 0.0007705632597208023, "children": { "RLTrainer._checkpoint": { "total": 0.05453561060130596, "count": 1, "self": 0.05453561060130596 } } } } } } }