{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8711736798286438, "min": 0.8711736798286438, "max": 2.8654141426086426, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8337.1318359375, "min": 8337.1318359375, "max": 29344.70703125, "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": 12.12051773071289, "min": 0.269070029258728, "max": 12.12051773071289, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2363.5009765625, "min": 52.1995849609375, "max": 2431.69921875, "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": 0.06625216413828872, "min": 0.061788149571329276, "max": 0.07227457482447647, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26500865655315486, "min": 0.26500865655315486, "max": 0.35529357308291315, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2205083883714442, "min": 0.11424654862140397, "max": 0.27965626681552214, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8820335534857768, "min": 0.4569861944856159, "max": 1.3982813340776108, "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": 24.15909090909091, "min": 3.409090909090909, "max": 24.15909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1063.0, "min": 150.0, "max": 1313.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.15909090909091, "min": 3.409090909090909, "max": 24.15909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1063.0, "min": 150.0, "max": 1313.0, "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": "1705949004", "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": "1705949443" }, "total": 439.64270725400013, "count": 1, "self": 0.44179451400009384, "children": { "run_training.setup": { "total": 0.05288978299995506, "count": 1, "self": 0.05288978299995506 }, "TrainerController.start_learning": { "total": 439.1480229570001, "count": 1, "self": 0.554085080004711, "children": { "TrainerController._reset_env": { "total": 3.4020523149999917, "count": 1, "self": 3.4020523149999917 }, "TrainerController.advance": { "total": 435.1033294899953, "count": 18201, "self": 0.2640948169910189, "children": { "env_step": { "total": 434.8392346730043, "count": 18201, "self": 283.67175248501917, "children": { "SubprocessEnvManager._take_step": { "total": 150.89509822300397, "count": 18201, "self": 1.4153974220259897, "children": { "TorchPolicy.evaluate": { "total": 149.47970080097798, "count": 18201, "self": 149.47970080097798 } } }, "workers": { "total": 0.27238396498114525, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 437.9191717339912, "count": 18201, "is_parallel": true, "self": 217.12891682799693, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005447924999998577, "count": 1, "is_parallel": true, "self": 0.004010269999980665, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014376550000179122, "count": 10, "is_parallel": true, "self": 0.0014376550000179122 } } }, "UnityEnvironment.step": { "total": 0.04600370200000725, "count": 1, "is_parallel": true, "self": 0.0007106979999207397, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040797600013320334, "count": 1, "is_parallel": true, "self": 0.00040797600013320334 }, "communicator.exchange": { "total": 0.042850650999980644, "count": 1, "is_parallel": true, "self": 0.042850650999980644 }, "steps_from_proto": { "total": 0.0020343769999726646, "count": 1, "is_parallel": true, "self": 0.0003965129999414785, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016378640000311862, "count": 10, "is_parallel": true, "self": 0.0016378640000311862 } } } } } } }, "UnityEnvironment.step": { "total": 220.7902549059943, "count": 18200, "is_parallel": true, "self": 10.690381389969161, "children": { "UnityEnvironment._generate_step_input": { "total": 5.285332264989165, "count": 18200, "is_parallel": true, "self": 5.285332264989165 }, "communicator.exchange": { "total": 171.75145246600732, "count": 18200, "is_parallel": true, "self": 171.75145246600732 }, "steps_from_proto": { "total": 33.06308878502864, "count": 18200, "is_parallel": true, "self": 6.07691422502603, "children": { "_process_rank_one_or_two_observation": { "total": 26.98617456000261, "count": 182000, "is_parallel": true, "self": 26.98617456000261 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011106300007668324, "count": 1, "self": 0.00011106300007668324, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 429.71043072905036, "count": 655521, "is_parallel": true, "self": 13.850918582152417, "children": { "process_trajectory": { "total": 236.62326865589694, "count": 655521, "is_parallel": true, "self": 235.97034177689693, "children": { "RLTrainer._checkpoint": { "total": 0.652926879000006, "count": 4, "is_parallel": true, "self": 0.652926879000006 } } }, "_update_policy": { "total": 179.236243491001, "count": 90, "is_parallel": true, "self": 54.400401163001106, "children": { "TorchPPOOptimizer.update": { "total": 124.8358423279999, "count": 4587, "is_parallel": true, "self": 124.8358423279999 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0884450089999973, "count": 1, "self": 0.0010356079999382928, "children": { "RLTrainer._checkpoint": { "total": 0.087409401000059, "count": 1, "self": 0.087409401000059 } } } } } } }