{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9775980114936829, "min": 0.9775980114936829, "max": 2.868438243865967, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9344.859375, "min": 9344.859375, "max": 29407.228515625, "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": 13.06369686126709, "min": 0.2569177448749542, "max": 13.06369686126709, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2547.4208984375, "min": 49.842041015625, "max": 2656.0576171875, "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": 0.07040010618120683, "min": 0.06393664140527036, "max": 0.07810269055235218, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2816004247248273, "min": 0.25574656562108145, "max": 0.3905134527617609, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19200854945708723, "min": 0.10278939753063204, "max": 0.28446940207013893, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7680341978283489, "min": 0.41115759012252817, "max": 1.4223470103506948, "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": 25.386363636363637, "min": 3.0681818181818183, "max": 25.654545454545456, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1117.0, "min": 135.0, "max": 1411.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.386363636363637, "min": 3.0681818181818183, "max": 25.654545454545456, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1117.0, "min": 135.0, "max": 1411.0, "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": "1707736889", "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": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707737324" }, "total": 434.5084470899999, "count": 1, "self": 0.4953637569997227, "children": { "run_training.setup": { "total": 0.05832191200011039, "count": 1, "self": 0.05832191200011039 }, "TrainerController.start_learning": { "total": 433.95476142100006, "count": 1, "self": 0.5799785569997766, "children": { "TrainerController._reset_env": { "total": 3.499846531000003, "count": 1, "self": 3.499846531000003 }, "TrainerController.advance": { "total": 429.77628927400065, "count": 18200, "self": 0.25412800597496243, "children": { "env_step": { "total": 429.5221612680257, "count": 18200, "self": 276.32661661199654, "children": { "SubprocessEnvManager._take_step": { "total": 152.92884906001632, "count": 18200, "self": 1.3976463250198776, "children": { "TorchPolicy.evaluate": { "total": 151.53120273499644, "count": 18200, "self": 151.53120273499644 } } }, "workers": { "total": 0.26669559601282344, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 432.8948531890196, "count": 18200, "is_parallel": true, "self": 215.53400096901896, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005447448999802873, "count": 1, "is_parallel": true, "self": 0.004000499999847307, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014469489999555663, "count": 10, "is_parallel": true, "self": 0.0014469489999555663 } } }, "UnityEnvironment.step": { "total": 0.07215900999995029, "count": 1, "is_parallel": true, "self": 0.000620033000359399, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039112199988267093, "count": 1, "is_parallel": true, "self": 0.00039112199988267093 }, "communicator.exchange": { "total": 0.06911976599985792, "count": 1, "is_parallel": true, "self": 0.06911976599985792 }, "steps_from_proto": { "total": 0.002028088999850297, "count": 1, "is_parallel": true, "self": 0.00040113199975166935, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016269570000986278, "count": 10, "is_parallel": true, "self": 0.0016269570000986278 } } } } } } }, "UnityEnvironment.step": { "total": 217.36085222000065, "count": 18199, "is_parallel": true, "self": 10.51539231000993, "children": { "UnityEnvironment._generate_step_input": { "total": 5.267565717019352, "count": 18199, "is_parallel": true, "self": 5.267565717019352 }, "communicator.exchange": { "total": 168.63668272299287, "count": 18199, "is_parallel": true, "self": 168.63668272299287 }, "steps_from_proto": { "total": 32.9412114699785, "count": 18199, "is_parallel": true, "self": 5.978628688904564, "children": { "_process_rank_one_or_two_observation": { "total": 26.962582781073934, "count": 181990, "is_parallel": true, "self": 26.962582781073934 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00018702199986364576, "count": 1, "self": 0.00018702199986364576, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 424.16689463576745, "count": 651455, "is_parallel": true, "self": 14.417730705703207, "children": { "process_trajectory": { "total": 233.36193200206458, "count": 651455, "is_parallel": true, "self": 232.85125620706458, "children": { "RLTrainer._checkpoint": { "total": 0.5106757949999974, "count": 4, "is_parallel": true, "self": 0.5106757949999974 } } }, "_update_policy": { "total": 176.38723192799966, "count": 90, "is_parallel": true, "self": 49.12613017499598, "children": { "TorchPPOOptimizer.update": { "total": 127.26110175300369, "count": 4587, "is_parallel": true, "self": 127.26110175300369 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09846003699976791, "count": 1, "self": 0.0009064579999176203, "children": { "RLTrainer._checkpoint": { "total": 0.09755357899985029, "count": 1, "self": 0.09755357899985029 } } } } } } }