{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9097416996955872, "min": 0.9097416996955872, "max": 2.8561291694641113, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8686.2138671875, "min": 8686.2138671875, "max": 29406.705078125, "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": 12.939300537109375, "min": 0.20404373109340668, "max": 12.939300537109375, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2523.16357421875, "min": 39.5844841003418, "max": 2637.91552734375, "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": 0.06430884843755884, "min": 0.060400023008069015, "max": 0.07926259533411996, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25723539375023535, "min": 0.24708529376406585, "max": 0.3649479259409275, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20720019301070888, "min": 0.09998365630756369, "max": 0.27729172982713757, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8288007720428355, "min": 0.39993462523025475, "max": 1.3534835752318888, "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": 25.613636363636363, "min": 2.8863636363636362, "max": 25.636363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1127.0, "min": 127.0, "max": 1402.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.613636363636363, "min": 2.8863636363636362, "max": 25.636363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1127.0, "min": 127.0, "max": 1402.0, "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": "1685325564", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "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": "1685326060" }, "total": 496.04887372300004, "count": 1, "self": 0.44068853200008107, "children": { "run_training.setup": { "total": 0.03953635799996391, "count": 1, "self": 0.03953635799996391 }, "TrainerController.start_learning": { "total": 495.568648833, "count": 1, "self": 0.5851094679889002, "children": { "TrainerController._reset_env": { "total": 3.7503636939999296, "count": 1, "self": 3.7503636939999296 }, "TrainerController.advance": { "total": 491.09053135701106, "count": 18200, "self": 0.2886388830007718, "children": { "env_step": { "total": 490.8018924740103, "count": 18200, "self": 360.8211546270137, "children": { "SubprocessEnvManager._take_step": { "total": 129.68619981799827, "count": 18200, "self": 2.034804876999033, "children": { "TorchPolicy.evaluate": { "total": 127.65139494099924, "count": 18200, "self": 127.65139494099924 } } }, "workers": { "total": 0.2945380289983177, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 493.8547988120106, "count": 18200, "is_parallel": true, "self": 233.6749298560169, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005420605000040268, "count": 1, "is_parallel": true, "self": 0.0038385729999390605, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015820320001012078, "count": 10, "is_parallel": true, "self": 0.0015820320001012078 } } }, "UnityEnvironment.step": { "total": 0.047072139000079005, "count": 1, "is_parallel": true, "self": 0.0006026070001325934, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003378129999873636, "count": 1, "is_parallel": true, "self": 0.0003378129999873636 }, "communicator.exchange": { "total": 0.043608758000004855, "count": 1, "is_parallel": true, "self": 0.043608758000004855 }, "steps_from_proto": { "total": 0.0025229609999541935, "count": 1, "is_parallel": true, "self": 0.0004329690001441122, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020899919998100813, "count": 10, "is_parallel": true, "self": 0.0020899919998100813 } } } } } } }, "UnityEnvironment.step": { "total": 260.1798689559937, "count": 18199, "is_parallel": true, "self": 10.1972350499899, "children": { "UnityEnvironment._generate_step_input": { "total": 5.768460638005081, "count": 18199, "is_parallel": true, "self": 5.768460638005081 }, "communicator.exchange": { "total": 207.94043879700644, "count": 18199, "is_parallel": true, "self": 207.94043879700644 }, "steps_from_proto": { "total": 36.27373447099228, "count": 18199, "is_parallel": true, "self": 7.133339904981085, "children": { "_process_rank_one_or_two_observation": { "total": 29.140394566011196, "count": 181990, "is_parallel": true, "self": 29.140394566011196 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001248080000095797, "count": 1, "self": 0.0001248080000095797, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 487.15569071097525, "count": 476061, "is_parallel": true, "self": 10.781395587969087, "children": { "process_trajectory": { "total": 268.9741506040049, "count": 476061, "is_parallel": true, "self": 267.6196522430049, "children": { "RLTrainer._checkpoint": { "total": 1.354498360999969, "count": 4, "is_parallel": true, "self": 1.354498360999969 } } }, "_update_policy": { "total": 207.4001445190013, "count": 90, "is_parallel": true, "self": 82.47732352399714, "children": { "TorchPPOOptimizer.update": { "total": 124.92282099500414, "count": 4587, "is_parallel": true, "self": 124.92282099500414 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14251950600009877, "count": 1, "self": 0.000904272000070705, "children": { "RLTrainer._checkpoint": { "total": 0.14161523400002807, "count": 1, "self": 0.14161523400002807 } } } } } } }