{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0719128847122192, "min": 1.0719128847122192, "max": 2.8716042041778564, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10234.6240234375, "min": 10234.6240234375, "max": 29408.099609375, "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": 6.261226654052734, "min": 0.2014385163784027, "max": 6.261226654052734, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1220.939208984375, "min": 39.079071044921875, "max": 1273.552490234375, "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": 0.06377512114133924, "min": 0.060498719510695645, "max": 0.07181747271405424, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25510048456535694, "min": 0.24199487804278258, "max": 0.3558624240777492, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18611390764514607, "min": 0.0804574042513017, "max": 0.23859660339121724, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7444556305805843, "min": 0.3218296170052068, "max": 1.1929830169560862, "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": 24.75, "min": 2.6363636363636362, "max": 24.75, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1089.0, "min": 116.0, "max": 1350.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.75, "min": 2.6363636363636362, "max": 24.75, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1089.0, "min": 116.0, "max": 1350.0, "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": "1706264053", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1706264494" }, "total": 441.063588439, "count": 1, "self": 0.4437809170000264, "children": { "run_training.setup": { "total": 0.05304348300001038, "count": 1, "self": 0.05304348300001038 }, "TrainerController.start_learning": { "total": 440.56676403899996, "count": 1, "self": 0.5744756290058604, "children": { "TrainerController._reset_env": { "total": 3.6572458690000076, "count": 1, "self": 3.6572458690000076 }, "TrainerController.advance": { "total": 436.24698399399415, "count": 18199, "self": 0.27298356298251747, "children": { "env_step": { "total": 435.97400043101163, "count": 18199, "self": 282.42858947103093, "children": { "SubprocessEnvManager._take_step": { "total": 153.26059218998478, "count": 18199, "self": 1.4466002819892765, "children": { "TorchPolicy.evaluate": { "total": 151.8139919079955, "count": 18199, "self": 151.8139919079955 } } }, "workers": { "total": 0.2848187699959226, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 439.3352894399859, "count": 18199, "is_parallel": true, "self": 215.86843635999548, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004692659999932403, "count": 1, "is_parallel": true, "self": 0.003343517999951473, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013491419999809295, "count": 10, "is_parallel": true, "self": 0.0013491419999809295 } } }, "UnityEnvironment.step": { "total": 0.08700247100000524, "count": 1, "is_parallel": true, "self": 0.0006786179999380693, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037057800000184216, "count": 1, "is_parallel": true, "self": 0.00037057800000184216 }, "communicator.exchange": { "total": 0.08399667000003319, "count": 1, "is_parallel": true, "self": 0.08399667000003319 }, "steps_from_proto": { "total": 0.001956605000032141, "count": 1, "is_parallel": true, "self": 0.00044375899994975043, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015128460000823907, "count": 10, "is_parallel": true, "self": 0.0015128460000823907 } } } } } } }, "UnityEnvironment.step": { "total": 223.46685307999041, "count": 18198, "is_parallel": true, "self": 10.670212145982532, "children": { "UnityEnvironment._generate_step_input": { "total": 5.342426743995588, "count": 18198, "is_parallel": true, "self": 5.342426743995588 }, "communicator.exchange": { "total": 174.3778688300108, "count": 18198, "is_parallel": true, "self": 174.3778688300108 }, "steps_from_proto": { "total": 33.07634536000148, "count": 18198, "is_parallel": true, "self": 6.223214184002245, "children": { "_process_rank_one_or_two_observation": { "total": 26.853131175999238, "count": 181980, "is_parallel": true, "self": 26.853131175999238 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00019238699997004005, "count": 1, "self": 0.00019238699997004005, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 430.846173098995, "count": 675589, "is_parallel": true, "self": 13.862077374995579, "children": { "process_trajectory": { "total": 236.85369621399946, "count": 675589, "is_parallel": true, "self": 236.39252875799934, "children": { "RLTrainer._checkpoint": { "total": 0.461167456000112, "count": 4, "is_parallel": true, "self": 0.461167456000112 } } }, "_update_policy": { "total": 180.13039950999996, "count": 90, "is_parallel": true, "self": 52.07496506800021, "children": { "TorchPPOOptimizer.update": { "total": 128.05543444199975, "count": 4584, "is_parallel": true, "self": 128.05543444199975 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08786615999997593, "count": 1, "self": 0.0009775439998520596, "children": { "RLTrainer._checkpoint": { "total": 0.08688861600012387, "count": 1, "self": 0.08688861600012387 } } } } } } }