{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8992668390274048, "min": 0.8992668390274048, "max": 2.835941791534424, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8546.6318359375, "min": 8546.6318359375, "max": 28949.294921875, "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": 12.842257499694824, "min": 0.2990364730358124, "max": 12.893875122070312, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2504.240234375, "min": 58.0130729675293, "max": 2630.3505859375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07101828644825967, "min": 0.06539242659003804, "max": 0.07375374981175079, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28407314579303866, "min": 0.26156970636015214, "max": 0.36876874905875395, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19401681569277068, "min": 0.11187471461473217, "max": 0.28535330017992094, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7760672627710827, "min": 0.44749885845892867, "max": 1.390547234345885, "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": 25.15909090909091, "min": 2.8636363636363638, "max": 25.654545454545456, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1107.0, "min": 126.0, "max": 1411.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.15909090909091, "min": 2.8636363636363638, "max": 25.654545454545456, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1107.0, "min": 126.0, "max": 1411.0, "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": "1750126241", "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": "1750126659" }, "total": 417.4914362259999, "count": 1, "self": 0.6348607579998315, "children": { "run_training.setup": { "total": 0.022456529999999475, "count": 1, "self": 0.022456529999999475 }, "TrainerController.start_learning": { "total": 416.8341189380001, "count": 1, "self": 0.3251032429935776, "children": { "TrainerController._reset_env": { "total": 3.029872845, "count": 1, "self": 3.029872845 }, "TrainerController.advance": { "total": 413.3523538670064, "count": 18192, "self": 0.36960907704053625, "children": { "env_step": { "total": 296.9487271749738, "count": 18192, "self": 227.18268177297, "children": { "SubprocessEnvManager._take_step": { "total": 69.5711245920096, "count": 18192, "self": 1.2292392960071084, "children": { "TorchPolicy.evaluate": { "total": 68.34188529600249, "count": 18192, "self": 68.34188529600249 } } }, "workers": { "total": 0.19492080999418704, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 415.3657432799906, "count": 18192, "is_parallel": true, "self": 215.71234418599408, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005227716000035798, "count": 1, "is_parallel": true, "self": 0.0038734100002102423, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013543059998255558, "count": 10, "is_parallel": true, "self": 0.0013543059998255558 } } }, "UnityEnvironment.step": { "total": 0.03693929799999296, "count": 1, "is_parallel": true, "self": 0.0005740109999123888, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004343140000173662, "count": 1, "is_parallel": true, "self": 0.0004343140000173662 }, "communicator.exchange": { "total": 0.0341499380000414, "count": 1, "is_parallel": true, "self": 0.0341499380000414 }, "steps_from_proto": { "total": 0.0017810350000218023, "count": 1, "is_parallel": true, "self": 0.0003569929999684973, "children": { "_process_rank_one_or_two_observation": { "total": 0.001424042000053305, "count": 10, "is_parallel": true, "self": 0.001424042000053305 } } } } } } }, "UnityEnvironment.step": { "total": 199.65339909399654, "count": 18191, "is_parallel": true, "self": 9.692847882026399, "children": { "UnityEnvironment._generate_step_input": { "total": 5.354136743998424, "count": 18191, "is_parallel": true, "self": 5.354136743998424 }, "communicator.exchange": { "total": 153.29806828598532, "count": 18191, "is_parallel": true, "self": 153.29806828598532 }, "steps_from_proto": { "total": 31.308346181986394, "count": 18191, "is_parallel": true, "self": 5.532917254989798, "children": { "_process_rank_one_or_two_observation": { "total": 25.775428926996597, "count": 181910, "is_parallel": true, "self": 25.775428926996597 } } } } } } } } } } }, "trainer_advance": { "total": 116.03401761499208, "count": 18192, "self": 0.42596451199915464, "children": { "process_trajectory": { "total": 26.186562073992945, "count": 18192, "self": 25.676241108992826, "children": { "RLTrainer._checkpoint": { "total": 0.510320965000119, "count": 4, "self": 0.510320965000119 } } }, "_update_policy": { "total": 89.42149102899998, "count": 90, "self": 36.105724487001225, "children": { "TorchPPOOptimizer.update": { "total": 53.315766541998755, "count": 4587, "self": 53.315766541998755 } } } } } } }, "trainer_threads": { "total": 1.5280002116924152e-06, "count": 1, "self": 1.5280002116924152e-06 }, "TrainerController._save_models": { "total": 0.12678745499988509, "count": 1, "self": 0.0010639329998411995, "children": { "RLTrainer._checkpoint": { "total": 0.12572352200004389, "count": 1, "self": 0.12572352200004389 } } } } } } }