{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7520580291748047, "min": 0.7520580291748047, "max": 2.8477981090545654, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7147.5595703125, "min": 7147.5595703125, "max": 29070.322265625, "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": 13.131010055541992, "min": 0.33000990748405457, "max": 13.131010055541992, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2560.546875, "min": 64.02191925048828, "max": 2658.736083984375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06806634380065553, "min": 0.06173997795627014, "max": 0.07252701081874251, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2722653752026221, "min": 0.25974765927757665, "max": 0.36263505409371255, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2044831329554904, "min": 0.11893650314852815, "max": 0.34242405603621523, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8179325318219616, "min": 0.4757460125941126, "max": 1.4576207568832473, "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": 26.045454545454547, "min": 3.6136363636363638, "max": 26.045454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1146.0, "min": 159.0, "max": 1412.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.045454545454547, "min": 3.6136363636363638, "max": 26.045454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1146.0, "min": 159.0, "max": 1412.0, "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": "1746253411", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1746253790" }, "total": 378.6090239619999, "count": 1, "self": 0.32138472300005105, "children": { "run_training.setup": { "total": 0.020847966999895107, "count": 1, "self": 0.020847966999895107 }, "TrainerController.start_learning": { "total": 378.266791272, "count": 1, "self": 0.3496371730049077, "children": { "TrainerController._reset_env": { "total": 2.2328333740000517, "count": 1, "self": 2.2328333740000517 }, "TrainerController.advance": { "total": 375.6050460069947, "count": 18192, "self": 0.3507884239896839, "children": { "env_step": { "total": 260.99048199699894, "count": 18192, "self": 195.77284246699026, "children": { "SubprocessEnvManager._take_step": { "total": 65.00955214800649, "count": 18192, "self": 1.1892764419942523, "children": { "TorchPolicy.evaluate": { "total": 63.82027570601224, "count": 18192, "self": 63.82027570601224 } } }, "workers": { "total": 0.20808738200219068, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 377.5047654209965, "count": 18192, "is_parallel": true, "self": 205.13931211299086, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026334570000017266, "count": 1, "is_parallel": true, "self": 0.0007442230000833661, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018892339999183605, "count": 10, "is_parallel": true, "self": 0.0018892339999183605 } } }, "UnityEnvironment.step": { "total": 0.028327417000014066, "count": 1, "is_parallel": true, "self": 0.00039694500003406574, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00026812800001607684, "count": 1, "is_parallel": true, "self": 0.00026812800001607684 }, "communicator.exchange": { "total": 0.026448834999996507, "count": 1, "is_parallel": true, "self": 0.026448834999996507 }, "steps_from_proto": { "total": 0.0012135089999674165, "count": 1, "is_parallel": true, "self": 0.0002677590000530472, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009457499999143693, "count": 10, "is_parallel": true, "self": 0.0009457499999143693 } } } } } } }, "UnityEnvironment.step": { "total": 172.3654533080056, "count": 18191, "is_parallel": true, "self": 6.117320842987738, "children": { "UnityEnvironment._generate_step_input": { "total": 3.2777932440022823, "count": 18191, "is_parallel": true, "self": 3.2777932440022823 }, "communicator.exchange": { "total": 143.11975104199985, "count": 18191, "is_parallel": true, "self": 143.11975104199985 }, "steps_from_proto": { "total": 19.850588179015745, "count": 18191, "is_parallel": true, "self": 3.9269575080171535, "children": { "_process_rank_one_or_two_observation": { "total": 15.923630670998591, "count": 181910, "is_parallel": true, "self": 15.923630670998591 } } } } } } } } } } }, "trainer_advance": { "total": 114.26377558600609, "count": 18192, "self": 0.4459701729927019, "children": { "process_trajectory": { "total": 25.06161602301404, "count": 18192, "self": 24.69135717801373, "children": { "RLTrainer._checkpoint": { "total": 0.3702588450003077, "count": 4, "self": 0.3702588450003077 } } }, "_update_policy": { "total": 88.75618938999935, "count": 90, "self": 35.94869212899812, "children": { "TorchPPOOptimizer.update": { "total": 52.80749726100123, "count": 4587, "self": 52.80749726100123 } } } } } } }, "trainer_threads": { "total": 1.0160001693293452e-06, "count": 1, "self": 1.0160001693293452e-06 }, "TrainerController._save_models": { "total": 0.07927370200013684, "count": 1, "self": 0.0007795360002091911, "children": { "RLTrainer._checkpoint": { "total": 0.07849416599992765, "count": 1, "self": 0.07849416599992765 } } } } } } }