{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0093581676483154, "min": 1.0093581676483154, "max": 2.862772226333618, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9637.3515625, "min": 9637.3515625, "max": 29317.650390625, "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": 12.678901672363281, "min": 0.40164196491241455, "max": 12.678901672363281, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2472.3857421875, "min": 77.91854095458984, "max": 2577.37353515625, "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": 0.06178664127361901, "min": 0.06178664127361901, "max": 0.0732315830690912, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24714656509447605, "min": 0.24714656509447605, "max": 0.36615791534545594, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19689024831442273, "min": 0.12969670665117125, "max": 0.28181594253755077, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7875609932576909, "min": 0.518786826604685, "max": 1.409079712687754, "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": 24.636363636363637, "min": 3.5454545454545454, "max": 25.01818181818182, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1084.0, "min": 156.0, "max": 1376.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.636363636363637, "min": 3.5454545454545454, "max": 25.01818181818182, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1084.0, "min": 156.0, "max": 1376.0, "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": "1706260360", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1706260859" }, "total": 498.871631297, "count": 1, "self": 0.49135728100009146, "children": { "run_training.setup": { "total": 0.05205020799985505, "count": 1, "self": 0.05205020799985505 }, "TrainerController.start_learning": { "total": 498.3282238080001, "count": 1, "self": 0.683415181978944, "children": { "TrainerController._reset_env": { "total": 3.5844158190000144, "count": 1, "self": 3.5844158190000144 }, "TrainerController.advance": { "total": 493.966903444021, "count": 18199, "self": 0.35361463900790113, "children": { "env_step": { "total": 493.6132888050131, "count": 18199, "self": 323.35639097201556, "children": { "SubprocessEnvManager._take_step": { "total": 169.91617849099634, "count": 18199, "self": 1.6694165620422154, "children": { "TorchPolicy.evaluate": { "total": 168.24676192895413, "count": 18199, "self": 168.24676192895413 } } }, "workers": { "total": 0.3407193420011936, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 496.9305026200075, "count": 18199, "is_parallel": true, "self": 242.7412574970058, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007566354000118736, "count": 1, "is_parallel": true, "self": 0.0046922750000248925, "children": { "_process_rank_one_or_two_observation": { "total": 0.002874079000093843, "count": 10, "is_parallel": true, "self": 0.002874079000093843 } } }, "UnityEnvironment.step": { "total": 0.042942058999869914, "count": 1, "is_parallel": true, "self": 0.0006713109999054723, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045450700008586864, "count": 1, "is_parallel": true, "self": 0.00045450700008586864 }, "communicator.exchange": { "total": 0.03969299699997464, "count": 1, "is_parallel": true, "self": 0.03969299699997464 }, "steps_from_proto": { "total": 0.0021232439999039343, "count": 1, "is_parallel": true, "self": 0.0004195700000764191, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017036739998275152, "count": 10, "is_parallel": true, "self": 0.0017036739998275152 } } } } } } }, "UnityEnvironment.step": { "total": 254.18924512300168, "count": 18198, "is_parallel": true, "self": 11.938386657002638, "children": { "UnityEnvironment._generate_step_input": { "total": 6.062407921985368, "count": 18198, "is_parallel": true, "self": 6.062407921985368 }, "communicator.exchange": { "total": 197.44701364200273, "count": 18198, "is_parallel": true, "self": 197.44701364200273 }, "steps_from_proto": { "total": 38.741436902010946, "count": 18198, "is_parallel": true, "self": 7.497250938010666, "children": { "_process_rank_one_or_two_observation": { "total": 31.24418596400028, "count": 181980, "is_parallel": true, "self": 31.24418596400028 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001694530001259409, "count": 1, "self": 0.0001694530001259409, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 487.63922820198377, "count": 708587, "is_parallel": true, "self": 16.975397764962054, "children": { "process_trajectory": { "total": 271.09843813202247, "count": 708587, "is_parallel": true, "self": 270.59549241002264, "children": { "RLTrainer._checkpoint": { "total": 0.5029457219998221, "count": 4, "is_parallel": true, "self": 0.5029457219998221 } } }, "_update_policy": { "total": 199.56539230499925, "count": 90, "is_parallel": true, "self": 56.77839562299391, "children": { "TorchPPOOptimizer.update": { "total": 142.78699668200534, "count": 4587, "is_parallel": true, "self": 142.78699668200534 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09331990999999107, "count": 1, "self": 0.0010198569998465246, "children": { "RLTrainer._checkpoint": { "total": 0.09230005300014454, "count": 1, "self": 0.09230005300014454 } } } } } } }