{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9168418049812317, "min": 0.9129596948623657, "max": 2.8644962310791016, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8804.431640625, "min": 8804.431640625, "max": 29335.3046875, "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": 13.077005386352539, "min": 0.3980576694011688, "max": 13.077005386352539, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2550.01611328125, "min": 77.22319030761719, "max": 2648.716552734375, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0682997923517998, "min": 0.06374630168749149, "max": 0.07602542667083588, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2731991694071992, "min": 0.263664395647128, "max": 0.3801271333541794, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19872159255193728, "min": 0.12438573318478816, "max": 0.2811551515378204, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7948863702077491, "min": 0.4975429327391526, "max": 1.405775757689102, "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": 25.59090909090909, "min": 3.227272727272727, "max": 25.963636363636365, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1126.0, "min": 142.0, "max": 1428.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.59090909090909, "min": 3.227272727272727, "max": 25.963636363636365, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1126.0, "min": 142.0, "max": 1428.0, "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": "1700716126", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700716595" }, "total": 469.650494622, "count": 1, "self": 0.7525461940001605, "children": { "run_training.setup": { "total": 0.04430020299992066, "count": 1, "self": 0.04430020299992066 }, "TrainerController.start_learning": { "total": 468.8536482249999, "count": 1, "self": 0.5365549380044285, "children": { "TrainerController._reset_env": { "total": 10.195860581000034, "count": 1, "self": 10.195860581000034 }, "TrainerController.advance": { "total": 457.99785449099545, "count": 18214, "self": 0.24418119999040755, "children": { "env_step": { "total": 457.75367329100504, "count": 18214, "self": 315.7044356100205, "children": { "SubprocessEnvManager._take_step": { "total": 141.78521306197945, "count": 18214, "self": 1.3839620749706683, "children": { "TorchPolicy.evaluate": { "total": 140.40125098700878, "count": 18214, "self": 140.40125098700878 } } }, "workers": { "total": 0.264024619005113, "count": 18214, "self": 0.0, "children": { "worker_root": { "total": 467.5688730660072, "count": 18214, "is_parallel": true, "self": 231.27804464300834, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006154550000019299, "count": 1, "is_parallel": true, "self": 0.004789921000110553, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013646289999087458, "count": 10, "is_parallel": true, "self": 0.0013646289999087458 } } }, "UnityEnvironment.step": { "total": 0.0371022830001948, "count": 1, "is_parallel": true, "self": 0.0004502620004132041, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003913640000519081, "count": 1, "is_parallel": true, "self": 0.0003913640000519081 }, "communicator.exchange": { "total": 0.03423465299988493, "count": 1, "is_parallel": true, "self": 0.03423465299988493 }, "steps_from_proto": { "total": 0.002026003999844761, "count": 1, "is_parallel": true, "self": 0.00038241999982346897, "children": { "_process_rank_one_or_two_observation": { "total": 0.001643584000021292, "count": 10, "is_parallel": true, "self": 0.001643584000021292 } } } } } } }, "UnityEnvironment.step": { "total": 236.29082842299886, "count": 18213, "is_parallel": true, "self": 10.484543741002426, "children": { "UnityEnvironment._generate_step_input": { "total": 5.231914081013656, "count": 18213, "is_parallel": true, "self": 5.231914081013656 }, "communicator.exchange": { "total": 187.13060726098183, "count": 18213, "is_parallel": true, "self": 187.13060726098183 }, "steps_from_proto": { "total": 33.44376334000094, "count": 18213, "is_parallel": true, "self": 6.136748836950574, "children": { "_process_rank_one_or_two_observation": { "total": 27.307014503050368, "count": 182130, "is_parallel": true, "self": 27.307014503050368 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001314589999310556, "count": 1, "self": 0.0001314589999310556, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 454.1870975040106, "count": 488437, "is_parallel": true, "self": 10.083063934941265, "children": { "process_trajectory": { "total": 256.1913897320703, "count": 488437, "is_parallel": true, "self": 255.20326431907029, "children": { "RLTrainer._checkpoint": { "total": 0.9881254130000343, "count": 4, "is_parallel": true, "self": 0.9881254130000343 } } }, "_update_policy": { "total": 187.912643836999, "count": 90, "is_parallel": true, "self": 65.12711896400924, "children": { "TorchPPOOptimizer.update": { "total": 122.78552487298975, "count": 4587, "is_parallel": true, "self": 122.78552487298975 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1232467560000714, "count": 1, "self": 0.0010992759998771362, "children": { "RLTrainer._checkpoint": { "total": 0.12214748000019426, "count": 1, "self": 0.12214748000019426 } } } } } } }