{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.93858402967453, "min": 0.9381951093673706, "max": 2.855163097381592, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8920.302734375, "min": 8920.302734375, "max": 29145.505859375, "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": 13.028555870056152, "min": 0.22255554795265198, "max": 13.168334007263184, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2540.568359375, "min": 43.175777435302734, "max": 2675.109130859375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07085627353704052, "min": 0.06311401027253619, "max": 0.07453971753084082, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2834250941481621, "min": 0.25669352444717386, "max": 0.3726985876542041, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2049303304623155, "min": 0.11385138727742813, "max": 0.2907550580945669, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.819721321849262, "min": 0.45540554910971254, "max": 1.4537752904728347, "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": 25.636363636363637, "min": 3.159090909090909, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1128.0, "min": 139.0, "max": 1408.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.636363636363637, "min": 3.159090909090909, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1128.0, "min": 139.0, "max": 1408.0, "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": "1765292100", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1765292531" }, "total": 431.09486953399994, "count": 1, "self": 0.45635997100004033, "children": { "run_training.setup": { "total": 0.02853052799997613, "count": 1, "self": 0.02853052799997613 }, "TrainerController.start_learning": { "total": 430.6099790349999, "count": 1, "self": 0.36993267999810087, "children": { "TrainerController._reset_env": { "total": 2.9919691729999727, "count": 1, "self": 2.9919691729999727 }, "TrainerController.advance": { "total": 427.172027307002, "count": 18192, "self": 0.37337630300208957, "children": { "env_step": { "total": 307.2579274629968, "count": 18192, "self": 240.22777558101262, "children": { "SubprocessEnvManager._take_step": { "total": 66.81600318699032, "count": 18192, "self": 1.223164534997295, "children": { "TorchPolicy.evaluate": { "total": 65.59283865199302, "count": 18192, "self": 65.59283865199302 } } }, "workers": { "total": 0.21414869499386668, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 428.8243224040022, "count": 18192, "is_parallel": true, "self": 217.72335200300108, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00480691399997113, "count": 1, "is_parallel": true, "self": 0.0031462840000244796, "children": { "_process_rank_one_or_two_observation": { "total": 0.00166062999994665, "count": 10, "is_parallel": true, "self": 0.00166062999994665 } } }, "UnityEnvironment.step": { "total": 0.03822777399994948, "count": 1, "is_parallel": true, "self": 0.0006076789999269749, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040461600002572595, "count": 1, "is_parallel": true, "self": 0.00040461600002572595 }, "communicator.exchange": { "total": 0.03533407200001193, "count": 1, "is_parallel": true, "self": 0.03533407200001193 }, "steps_from_proto": { "total": 0.001881406999984847, "count": 1, "is_parallel": true, "self": 0.00035480900010043115, "children": { "_process_rank_one_or_two_observation": { "total": 0.001526597999884416, "count": 10, "is_parallel": true, "self": 0.001526597999884416 } } } } } } }, "UnityEnvironment.step": { "total": 211.10097040100112, "count": 18191, "is_parallel": true, "self": 10.162003957997342, "children": { "UnityEnvironment._generate_step_input": { "total": 5.269964363002032, "count": 18191, "is_parallel": true, "self": 5.269964363002032 }, "communicator.exchange": { "total": 161.3208723760008, "count": 18191, "is_parallel": true, "self": 161.3208723760008 }, "steps_from_proto": { "total": 34.34812970400094, "count": 18191, "is_parallel": true, "self": 6.313504672021509, "children": { "_process_rank_one_or_two_observation": { "total": 28.03462503197943, "count": 181910, "is_parallel": true, "self": 28.03462503197943 } } } } } } } } } } }, "trainer_advance": { "total": 119.5407235410031, "count": 18192, "self": 0.4591195909992507, "children": { "process_trajectory": { "total": 25.35896765400406, "count": 18192, "self": 24.87555691500421, "children": { "RLTrainer._checkpoint": { "total": 0.48341073899985076, "count": 4, "self": 0.48341073899985076 } } }, "_update_policy": { "total": 93.72263629599979, "count": 90, "self": 38.87211589900204, "children": { "TorchPPOOptimizer.update": { "total": 54.85052039699775, "count": 4587, "self": 54.85052039699775 } } } } } } }, "trainer_threads": { "total": 8.909998996387003e-07, "count": 1, "self": 8.909998996387003e-07 }, "TrainerController._save_models": { "total": 0.07604898399995363, "count": 1, "self": 0.0007239779998826634, "children": { "RLTrainer._checkpoint": { "total": 0.07532500600007097, "count": 1, "self": 0.07532500600007097 } } } } } } }