{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.029302716255188, "min": 1.0240780115127563, "max": 2.8560564517974854, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9895.716796875, "min": 9895.716796875, "max": 29217.45703125, "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": 13.019500732421875, "min": 0.22499829530715942, "max": 13.019500732421875, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2538.802734375, "min": 43.6496696472168, "max": 2641.07470703125, "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": 0.07304217521128771, "min": 0.061398834488000806, "max": 0.07426455938063252, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29216870084515084, "min": 0.24559533795200322, "max": 0.3497124540439222, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.194112524901535, "min": 0.11946431347214637, "max": 0.2804828888645359, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.77645009960614, "min": 0.47785725388858546, "max": 1.4024144443226794, "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": 25.40909090909091, "min": 3.090909090909091, "max": 25.818181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1118.0, "min": 136.0, "max": 1388.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.40909090909091, "min": 3.090909090909091, "max": 25.818181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1118.0, "min": 136.0, "max": 1388.0, "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": "1680865279", "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=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": "1680865753" }, "total": 473.7233298110001, "count": 1, "self": 0.8142048960002057, "children": { "run_training.setup": { "total": 0.18671183399999336, "count": 1, "self": 0.18671183399999336 }, "TrainerController.start_learning": { "total": 472.7224130809999, "count": 1, "self": 0.5607068979825272, "children": { "TrainerController._reset_env": { "total": 4.497891417999995, "count": 1, "self": 4.497891417999995 }, "TrainerController.advance": { "total": 467.4232378460172, "count": 18217, "self": 0.2900968560259116, "children": { "env_step": { "total": 467.13314098999126, "count": 18217, "self": 340.4526487199978, "children": { "SubprocessEnvManager._take_step": { "total": 126.39063621599666, "count": 18217, "self": 1.972940481000819, "children": { "TorchPolicy.evaluate": { "total": 124.41769573499585, "count": 18217, "self": 124.41769573499585 } } }, "workers": { "total": 0.28985605399680026, "count": 18217, "self": 0.0, "children": { "worker_root": { "total": 471.0290793510069, "count": 18217, "is_parallel": true, "self": 218.4655587439995, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006732134000003498, "count": 1, "is_parallel": true, "self": 0.004217735999759498, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025143980002440003, "count": 10, "is_parallel": true, "self": 0.0025143980002440003 } } }, "UnityEnvironment.step": { "total": 0.03874084000005951, "count": 1, "is_parallel": true, "self": 0.0006404309999652469, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037495800006581703, "count": 1, "is_parallel": true, "self": 0.00037495800006581703 }, "communicator.exchange": { "total": 0.035696420000022044, "count": 1, "is_parallel": true, "self": 0.035696420000022044 }, "steps_from_proto": { "total": 0.0020290310000063982, "count": 1, "is_parallel": true, "self": 0.0004322169999113612, "children": { "_process_rank_one_or_two_observation": { "total": 0.001596814000095037, "count": 10, "is_parallel": true, "self": 0.001596814000095037 } } } } } } }, "UnityEnvironment.step": { "total": 252.56352060700738, "count": 18216, "is_parallel": true, "self": 10.230820218043846, "children": { "UnityEnvironment._generate_step_input": { "total": 5.763670516990828, "count": 18216, "is_parallel": true, "self": 5.763670516990828 }, "communicator.exchange": { "total": 202.6950165509669, "count": 18216, "is_parallel": true, "self": 202.6950165509669 }, "steps_from_proto": { "total": 33.874013321005805, "count": 18216, "is_parallel": true, "self": 6.800747594961194, "children": { "_process_rank_one_or_two_observation": { "total": 27.07326572604461, "count": 182160, "is_parallel": true, "self": 27.07326572604461 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014423300012822438, "count": 1, "self": 0.00014423300012822438, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 463.83865586405216, "count": 416908, "is_parallel": true, "self": 10.467253584120954, "children": { "process_trajectory": { "total": 258.8561702479308, "count": 416908, "is_parallel": true, "self": 257.3073738349309, "children": { "RLTrainer._checkpoint": { "total": 1.5487964129998772, "count": 4, "is_parallel": true, "self": 1.5487964129998772 } } }, "_update_policy": { "total": 194.51523203200043, "count": 90, "is_parallel": true, "self": 71.1467811120001, "children": { "TorchPPOOptimizer.update": { "total": 123.36845092000033, "count": 4584, "is_parallel": true, "self": 123.36845092000033 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2404326860000765, "count": 1, "self": 0.0013856519999535521, "children": { "RLTrainer._checkpoint": { "total": 0.23904703400012295, "count": 1, "self": 0.23904703400012295 } } } } } } }