{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9593857526779175, "min": 0.9498782753944397, "max": 2.8788156509399414, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9191.875, "min": 9191.875, "max": 29513.6171875, "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": 13.205334663391113, "min": 0.4354381263256073, "max": 13.205334663391113, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2575.040283203125, "min": 84.4749984741211, "max": 2679.617919921875, "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": 0.06946192981444718, "min": 0.06214538616135114, "max": 0.07482993320302864, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27784771925778873, "min": 0.25064444603848124, "max": 0.37349947194382493, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20614630400257952, "min": 0.12997776126790356, "max": 0.27957061283728657, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8245852160103181, "min": 0.5199110450716142, "max": 1.3978530641864328, "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": 26.15909090909091, "min": 3.8636363636363638, "max": 26.15909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1151.0, "min": 170.0, "max": 1430.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.15909090909091, "min": 3.8636363636363638, "max": 26.15909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1151.0, "min": 170.0, "max": 1430.0, "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": "1693160797", "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": "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": "1693161270" }, "total": 472.99093223499995, "count": 1, "self": 0.8328840789999958, "children": { "run_training.setup": { "total": 0.04467707999992854, "count": 1, "self": 0.04467707999992854 }, "TrainerController.start_learning": { "total": 472.113371076, "count": 1, "self": 0.5802813300031175, "children": { "TrainerController._reset_env": { "total": 4.347673300999986, "count": 1, "self": 4.347673300999986 }, "TrainerController.advance": { "total": 466.9393407089967, "count": 18217, "self": 0.2721774340018328, "children": { "env_step": { "total": 466.6671632749949, "count": 18217, "self": 338.92875821598113, "children": { "SubprocessEnvManager._take_step": { "total": 127.458840268004, "count": 18217, "self": 1.9718767910046608, "children": { "TorchPolicy.evaluate": { "total": 125.48696347699934, "count": 18217, "self": 125.48696347699934 } } }, "workers": { "total": 0.2795647910097614, "count": 18217, "self": 0.0, "children": { "worker_root": { "total": 470.39041632499607, "count": 18217, "is_parallel": true, "self": 222.5170435269904, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007894754000062676, "count": 1, "is_parallel": true, "self": 0.00582183499977873, "children": { "_process_rank_one_or_two_observation": { "total": 0.002072919000283946, "count": 10, "is_parallel": true, "self": 0.002072919000283946 } } }, "UnityEnvironment.step": { "total": 0.05299805499998911, "count": 1, "is_parallel": true, "self": 0.0005379639999318897, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00034517700009928376, "count": 1, "is_parallel": true, "self": 0.00034517700009928376 }, "communicator.exchange": { "total": 0.04978126500009239, "count": 1, "is_parallel": true, "self": 0.04978126500009239 }, "steps_from_proto": { "total": 0.002333648999865545, "count": 1, "is_parallel": true, "self": 0.0004309789999297209, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019026699999358243, "count": 10, "is_parallel": true, "self": 0.0019026699999358243 } } } } } } }, "UnityEnvironment.step": { "total": 247.87337279800568, "count": 18216, "is_parallel": true, "self": 10.628170196975816, "children": { "UnityEnvironment._generate_step_input": { "total": 5.389983229010568, "count": 18216, "is_parallel": true, "self": 5.389983229010568 }, "communicator.exchange": { "total": 195.77810993700814, "count": 18216, "is_parallel": true, "self": 195.77810993700814 }, "steps_from_proto": { "total": 36.07710943501115, "count": 18216, "is_parallel": true, "self": 6.5762219680214, "children": { "_process_rank_one_or_two_observation": { "total": 29.500887466989752, "count": 182160, "is_parallel": true, "self": 29.500887466989752 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015786800008754653, "count": 1, "self": 0.00015786800008754653, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 463.3658425759447, "count": 439918, "is_parallel": true, "self": 9.521029598048926, "children": { "process_trajectory": { "total": 251.54221240289485, "count": 439918, "is_parallel": true, "self": 249.9808395878947, "children": { "RLTrainer._checkpoint": { "total": 1.5613728150001407, "count": 4, "is_parallel": true, "self": 1.5613728150001407 } } }, "_update_policy": { "total": 202.30260057500095, "count": 90, "is_parallel": true, "self": 83.72647889700238, "children": { "TorchPPOOptimizer.update": { "total": 118.57612167799857, "count": 4587, "is_parallel": true, "self": 118.57612167799857 } } } } } } } } }, "TrainerController._save_models": { "total": 0.24591786800010595, "count": 1, "self": 0.0011620260002018767, "children": { "RLTrainer._checkpoint": { "total": 0.24475584199990408, "count": 1, "self": 0.24475584199990408 } } } } } } }