{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9082556962966919, "min": 0.9082556962966919, "max": 2.863542079925537, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8672.025390625, "min": 8672.025390625, "max": 29357.033203125, "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": 13.022985458374023, "min": 0.31421148777008057, "max": 13.022985458374023, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2539.482177734375, "min": 60.95703125, "max": 2601.872802734375, "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": 0.0657943014419859, "min": 0.06464746453860368, "max": 0.07400116402719754, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2631772057679436, "min": 0.2585898581544147, "max": 0.3612559493916456, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19148988598117642, "min": 0.11208140058214686, "max": 0.2857801100202635, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7659595439247057, "min": 0.4483256023285874, "max": 1.4289005501013174, "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": 25.84090909090909, "min": 3.4318181818181817, "max": 25.84090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1137.0, "min": 151.0, "max": 1393.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.84090909090909, "min": 3.4318181818181817, "max": 25.84090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1137.0, "min": 151.0, "max": 1393.0, "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": "1691905892", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1691906362" }, "total": 470.2689513749999, "count": 1, "self": 0.43455819099995097, "children": { "run_training.setup": { "total": 0.041046836999953484, "count": 1, "self": 0.041046836999953484 }, "TrainerController.start_learning": { "total": 469.793346347, "count": 1, "self": 0.5434590779966584, "children": { "TrainerController._reset_env": { "total": 4.361796462000029, "count": 1, "self": 4.361796462000029 }, "TrainerController.advance": { "total": 464.7471421150034, "count": 18201, "self": 0.2759371029949307, "children": { "env_step": { "total": 464.47120501200845, "count": 18201, "self": 335.89330997501975, "children": { "SubprocessEnvManager._take_step": { "total": 128.28890310399424, "count": 18201, "self": 1.7547817069953453, "children": { "TorchPolicy.evaluate": { "total": 126.5341213969989, "count": 18201, "self": 126.5341213969989 } } }, "workers": { "total": 0.28899193299446324, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 468.33848770398754, "count": 18201, "is_parallel": true, "self": 219.81506295798306, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006901480999999876, "count": 1, "is_parallel": true, "self": 0.005310336999968968, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015911440000309085, "count": 10, "is_parallel": true, "self": 0.0015911440000309085 } } }, "UnityEnvironment.step": { "total": 0.06279430300003241, "count": 1, "is_parallel": true, "self": 0.0006245069999977204, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003699840000308541, "count": 1, "is_parallel": true, "self": 0.0003699840000308541 }, "communicator.exchange": { "total": 0.059704251999960434, "count": 1, "is_parallel": true, "self": 0.059704251999960434 }, "steps_from_proto": { "total": 0.002095560000043406, "count": 1, "is_parallel": true, "self": 0.00038247100019361824, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017130889998497878, "count": 10, "is_parallel": true, "self": 0.0017130889998497878 } } } } } } }, "UnityEnvironment.step": { "total": 248.52342474600448, "count": 18200, "is_parallel": true, "self": 10.570806769017508, "children": { "UnityEnvironment._generate_step_input": { "total": 5.246365741989848, "count": 18200, "is_parallel": true, "self": 5.246365741989848 }, "communicator.exchange": { "total": 196.84078917998977, "count": 18200, "is_parallel": true, "self": 196.84078917998977 }, "steps_from_proto": { "total": 35.86546305500735, "count": 18200, "is_parallel": true, "self": 6.568354531060436, "children": { "_process_rank_one_or_two_observation": { "total": 29.297108523946918, "count": 182000, "is_parallel": true, "self": 29.297108523946918 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001607090000561584, "count": 1, "self": 0.0001607090000561584, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 461.3971959679401, "count": 430766, "is_parallel": true, "self": 9.309354027968197, "children": { "process_trajectory": { "total": 252.9172014909717, "count": 430766, "is_parallel": true, "self": 251.8031943409718, "children": { "RLTrainer._checkpoint": { "total": 1.1140071499999067, "count": 4, "is_parallel": true, "self": 1.1140071499999067 } } }, "_update_policy": { "total": 199.1706404490002, "count": 90, "is_parallel": true, "self": 76.98435457100959, "children": { "TorchPPOOptimizer.update": { "total": 122.1862858779906, "count": 4587, "is_parallel": true, "self": 122.1862858779906 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14078798299988193, "count": 1, "self": 0.0008415769998464384, "children": { "RLTrainer._checkpoint": { "total": 0.1399464060000355, "count": 1, "self": 0.1399464060000355 } } } } } } }