{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.3657820224761963, "min": 1.3657820224761963, "max": 2.8814616203308105, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 13040.486328125, "min": 13040.486328125, "max": 29509.048828125, "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": 12.422035217285156, "min": 0.5063137412071228, "max": 12.422035217285156, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2422.296875, "min": 98.22486877441406, "max": 2510.35009765625, "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": 0.07248690631069407, "min": 0.06377157429119061, "max": 0.0742890913651197, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2899476252427763, "min": 0.25508629716476244, "max": 0.3714454568255985, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20028863467422187, "min": 0.11901058816104469, "max": 0.26494974672209987, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8011545386968875, "min": 0.47604235264417877, "max": 1.2758128000240703, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 5.388009730600003e-05, "min": 5.388009730600003e-05, "max": 0.001945880002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0002155203892240001, "min": 0.0002155203892240001, "max": 0.00923440003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.09999999999999998, "min": 0.09999999999999998, "max": 0.09999999999999998, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.3999999999999999, "min": 0.3999999999999999, "max": 0.4999999999999999, "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": 24.772727272727273, "min": 3.1136363636363638, "max": 24.90909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1090.0, "min": 137.0, "max": 1349.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.772727272727273, "min": 3.1136363636363638, "max": 24.90909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1090.0, "min": 137.0, "max": 1349.0, "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": "1679218020", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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=SnowballTarget2 --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": "1679218475" }, "total": 455.1994181780001, "count": 1, "self": 0.7272712530002536, "children": { "run_training.setup": { "total": 0.10010213699979431, "count": 1, "self": 0.10010213699979431 }, "TrainerController.start_learning": { "total": 454.37204478800004, "count": 1, "self": 0.5487199020112712, "children": { "TrainerController._reset_env": { "total": 5.719490780999877, "count": 1, "self": 5.719490780999877 }, "TrainerController.advance": { "total": 447.8756048009891, "count": 18212, "self": 0.2805861969495709, "children": { "env_step": { "total": 447.5950186040395, "count": 18212, "self": 324.19736295908706, "children": { "SubprocessEnvManager._take_step": { "total": 123.13395416901858, "count": 18212, "self": 1.8465203180162462, "children": { "TorchPolicy.evaluate": { "total": 121.28743385100233, "count": 18212, "self": 121.28743385100233 } } }, "workers": { "total": 0.2637014759338854, "count": 18212, "self": 0.0, "children": { "worker_root": { "total": 452.8898813449723, "count": 18212, "is_parallel": true, "self": 213.36200566694788, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019253939999543945, "count": 1, "is_parallel": true, "self": 0.0006357800002660952, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012896139996882994, "count": 10, "is_parallel": true, "self": 0.0012896139996882994 } } }, "UnityEnvironment.step": { "total": 0.04557048400010899, "count": 1, "is_parallel": true, "self": 0.0005901250001443259, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003715530001500156, "count": 1, "is_parallel": true, "self": 0.0003715530001500156 }, "communicator.exchange": { "total": 0.04270577699981004, "count": 1, "is_parallel": true, "self": 0.04270577699981004 }, "steps_from_proto": { "total": 0.001903029000004608, "count": 1, "is_parallel": true, "self": 0.0005148420000296028, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013881869999750052, "count": 10, "is_parallel": true, "self": 0.0013881869999750052 } } } } } } }, "UnityEnvironment.step": { "total": 239.52787567802443, "count": 18211, "is_parallel": true, "self": 9.361195565980324, "children": { "UnityEnvironment._generate_step_input": { "total": 5.033057282023492, "count": 18211, "is_parallel": true, "self": 5.033057282023492 }, "communicator.exchange": { "total": 195.07069511900363, "count": 18211, "is_parallel": true, "self": 195.07069511900363 }, "steps_from_proto": { "total": 30.062927711016982, "count": 18211, "is_parallel": true, "self": 5.953288311899087, "children": { "_process_rank_one_or_two_observation": { "total": 24.109639399117896, "count": 182110, "is_parallel": true, "self": 24.109639399117896 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011423099977037054, "count": 1, "self": 0.00011423099977037054, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 444.7551320571033, "count": 390689, "is_parallel": true, "self": 9.272329466279643, "children": { "process_trajectory": { "total": 244.8193140678236, "count": 390689, "is_parallel": true, "self": 243.39723775682432, "children": { "RLTrainer._checkpoint": { "total": 1.4220763109992731, "count": 4, "is_parallel": true, "self": 1.4220763109992731 } } }, "_update_policy": { "total": 190.66348852300007, "count": 90, "is_parallel": true, "self": 73.08300338100662, "children": { "TorchPPOOptimizer.update": { "total": 117.58048514199345, "count": 4587, "is_parallel": true, "self": 117.58048514199345 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2281150730000263, "count": 1, "self": 0.001159741999799735, "children": { "RLTrainer._checkpoint": { "total": 0.22695533100022658, "count": 1, "self": 0.22695533100022658 } } } } } } }