{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9747664332389832, "min": 0.9747664332389832, "max": 2.8729183673858643, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9328.5146484375, "min": 9328.5146484375, "max": 29516.36328125, "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": 12.462470054626465, "min": 0.33048760890960693, "max": 12.462470054626465, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2430.181640625, "min": 64.11459350585938, "max": 2510.05908203125, "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.Losses.PolicyLoss.mean": { "value": 0.07068380439059362, "min": 0.05994335694007995, "max": 0.07824516586055431, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28273521756237446, "min": 0.2537526066401316, "max": 0.39122582930277155, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18871744765954857, "min": 0.13551886437584043, "max": 0.2731415246631585, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7548697906381943, "min": 0.5420754575033617, "max": 1.349476363144669, "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": 24.886363636363637, "min": 3.5, "max": 24.886363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1095.0, "min": 154.0, "max": 1351.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.886363636363637, "min": 3.5, "max": 24.886363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1095.0, "min": 154.0, "max": 1351.0, "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": "1690662626", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1690663266" }, "total": 640.214765435, "count": 1, "self": 0.5970155190001378, "children": { "run_training.setup": { "total": 0.07455905199992685, "count": 1, "self": 0.07455905199992685 }, "TrainerController.start_learning": { "total": 639.5431908639999, "count": 1, "self": 0.9117383759930817, "children": { "TrainerController._reset_env": { "total": 3.3792768350000415, "count": 1, "self": 3.3792768350000415 }, "TrainerController.advance": { "total": 635.0966380270067, "count": 18206, "self": 0.4221789920112542, "children": { "env_step": { "total": 634.6744590349955, "count": 18206, "self": 513.281243198985, "children": { "SubprocessEnvManager._take_step": { "total": 120.95407538400855, "count": 18206, "self": 3.3338250540000445, "children": { "TorchPolicy.evaluate": { "total": 117.6202503300085, "count": 18206, "self": 117.6202503300085 } } }, "workers": { "total": 0.43914045200199325, "count": 18206, "self": 0.0, "children": { "worker_root": { "total": 636.9861628409997, "count": 18206, "is_parallel": true, "self": 274.6434733309993, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.010113247999925079, "count": 1, "is_parallel": true, "self": 0.007218323999950371, "children": { "_process_rank_one_or_two_observation": { "total": 0.002894923999974708, "count": 10, "is_parallel": true, "self": 0.002894923999974708 } } }, "UnityEnvironment.step": { "total": 0.04382355899997492, "count": 1, "is_parallel": true, "self": 0.0007877159998770367, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003346890000557323, "count": 1, "is_parallel": true, "self": 0.0003346890000557323 }, "communicator.exchange": { "total": 0.04005275800000163, "count": 1, "is_parallel": true, "self": 0.04005275800000163 }, "steps_from_proto": { "total": 0.0026483960000405204, "count": 1, "is_parallel": true, "self": 0.000508813999999802, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021395820000407184, "count": 10, "is_parallel": true, "self": 0.0021395820000407184 } } } } } } }, "UnityEnvironment.step": { "total": 362.34268951000035, "count": 18205, "is_parallel": true, "self": 15.773961005000274, "children": { "UnityEnvironment._generate_step_input": { "total": 8.09556127500207, "count": 18205, "is_parallel": true, "self": 8.09556127500207 }, "communicator.exchange": { "total": 288.5598969420017, "count": 18205, "is_parallel": true, "self": 288.5598969420017 }, "steps_from_proto": { "total": 49.91327028799628, "count": 18205, "is_parallel": true, "self": 10.012864087990351, "children": { "_process_rank_one_or_two_observation": { "total": 39.90040620000593, "count": 182050, "is_parallel": true, "self": 39.90040620000593 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0006433000000924949, "count": 1, "self": 0.0006433000000924949, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 628.8566941850113, "count": 639557, "is_parallel": true, "self": 17.08246083801714, "children": { "process_trajectory": { "total": 340.80117449999454, "count": 639557, "is_parallel": true, "self": 339.0573186499946, "children": { "RLTrainer._checkpoint": { "total": 1.7438558499999317, "count": 4, "is_parallel": true, "self": 1.7438558499999317 } } }, "_update_policy": { "total": 270.9730588469996, "count": 90, "is_parallel": true, "self": 100.05192490500133, "children": { "TorchPPOOptimizer.update": { "total": 170.92113394199828, "count": 4587, "is_parallel": true, "self": 170.92113394199828 } } } } } } } } }, "TrainerController._save_models": { "total": 0.154894325999976, "count": 1, "self": 0.0011063439999361435, "children": { "RLTrainer._checkpoint": { "total": 0.15378798200003985, "count": 1, "self": 0.15378798200003985 } } } } } } }