{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0355017185211182, "min": 1.0355017185211182, "max": 2.8576772212982178, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9886.970703125, "min": 9886.970703125, "max": 29265.47265625, "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": 12.779973983764648, "min": 0.41742467880249023, "max": 12.779973983764648, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2492.094970703125, "min": 80.98038482666016, "max": 2609.20751953125, "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": 0.07098959383766473, "min": 0.06109983080538108, "max": 0.07663115477029636, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28395837535065893, "min": 0.2456770374243991, "max": 0.3831557738514818, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19264440852053025, "min": 0.13478406366558893, "max": 0.2893913909500721, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.770577634082121, "min": 0.5391362546623557, "max": 1.4469569547503605, "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": 25.431818181818183, "min": 3.522727272727273, "max": 25.6, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1119.0, "min": 155.0, "max": 1408.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.431818181818183, "min": 3.522727272727273, "max": 25.6, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1119.0, "min": 155.0, "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": "1686625159", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1686625682" }, "total": 522.820177909, "count": 1, "self": 0.38218695999989905, "children": { "run_training.setup": { "total": 0.04259765100005097, "count": 1, "self": 0.04259765100005097 }, "TrainerController.start_learning": { "total": 522.395393298, "count": 1, "self": 0.6848932890032984, "children": { "TrainerController._reset_env": { "total": 5.384006639999939, "count": 1, "self": 5.384006639999939 }, "TrainerController.advance": { "total": 516.1826538519967, "count": 18201, "self": 0.3403555309856756, "children": { "env_step": { "total": 515.8422983210111, "count": 18201, "self": 373.86585574699984, "children": { "SubprocessEnvManager._take_step": { "total": 141.64007965500696, "count": 18201, "self": 1.9680660550189941, "children": { "TorchPolicy.evaluate": { "total": 139.67201359998796, "count": 18201, "self": 139.67201359998796 } } }, "workers": { "total": 0.33636291900427295, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 520.4989945980063, "count": 18201, "is_parallel": true, "self": 242.125804385003, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006004211000004034, "count": 1, "is_parallel": true, "self": 0.004223711999884472, "children": { "_process_rank_one_or_two_observation": { "total": 0.001780499000119562, "count": 10, "is_parallel": true, "self": 0.001780499000119562 } } }, "UnityEnvironment.step": { "total": 0.12613462600006642, "count": 1, "is_parallel": true, "self": 0.0006675670000504397, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004660710000052859, "count": 1, "is_parallel": true, "self": 0.0004660710000052859 }, "communicator.exchange": { "total": 0.11748084099997413, "count": 1, "is_parallel": true, "self": 0.11748084099997413 }, "steps_from_proto": { "total": 0.007520147000036559, "count": 1, "is_parallel": true, "self": 0.00042153000003963825, "children": { "_process_rank_one_or_two_observation": { "total": 0.007098616999996921, "count": 10, "is_parallel": true, "self": 0.007098616999996921 } } } } } } }, "UnityEnvironment.step": { "total": 278.37319021300334, "count": 18200, "is_parallel": true, "self": 11.542958700008512, "children": { "UnityEnvironment._generate_step_input": { "total": 6.053954260992214, "count": 18200, "is_parallel": true, "self": 6.053954260992214 }, "communicator.exchange": { "total": 220.74810896900226, "count": 18200, "is_parallel": true, "self": 220.74810896900226 }, "steps_from_proto": { "total": 40.028168283000355, "count": 18200, "is_parallel": true, "self": 7.627361865978287, "children": { "_process_rank_one_or_two_observation": { "total": 32.40080641702207, "count": 182000, "is_parallel": true, "self": 32.40080641702207 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001313889999892126, "count": 1, "self": 0.0001313889999892126, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 512.0761790920078, "count": 497881, "is_parallel": true, "self": 11.37992758103644, "children": { "process_trajectory": { "total": 285.2125860829708, "count": 497881, "is_parallel": true, "self": 284.3492187579708, "children": { "RLTrainer._checkpoint": { "total": 0.8633673250000129, "count": 4, "is_parallel": true, "self": 0.8633673250000129 } } }, "_update_policy": { "total": 215.48366542800056, "count": 90, "is_parallel": true, "self": 78.6402639300054, "children": { "TorchPPOOptimizer.update": { "total": 136.84340149799516, "count": 4587, "is_parallel": true, "self": 136.84340149799516 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14370812800007116, "count": 1, "self": 0.0008298950001517369, "children": { "RLTrainer._checkpoint": { "total": 0.14287823299991942, "count": 1, "self": 0.14287823299991942 } } } } } } }