{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8556022047996521, "min": 0.8556022047996521, "max": 2.8700356483459473, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8169.2900390625, "min": 8169.2900390625, "max": 29423.60546875, "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": 13.068727493286133, "min": 0.26404592394828796, "max": 13.068727493286133, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2548.40185546875, "min": 51.224910736083984, "max": 2640.281005859375, "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": 0.06690154017026846, "min": 0.06087034734550353, "max": 0.07387714716177844, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26760616068107385, "min": 0.26708611916504144, "max": 0.3579472522130042, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20043639086332976, "min": 0.10643959686835752, "max": 0.3168204552987043, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.801745563453319, "min": 0.4257583874734301, "max": 1.5841022764935213, "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": 3.1136363636363638, "max": 25.945454545454545, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1126.0, "min": 137.0, "max": 1427.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.59090909090909, "min": 3.1136363636363638, "max": 25.945454545454545, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1126.0, "min": 137.0, "max": 1427.0, "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": "1700132188", "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": "1700132672" }, "total": 484.36606093299997, "count": 1, "self": 0.42548592399998597, "children": { "run_training.setup": { "total": 0.047384445000005826, "count": 1, "self": 0.047384445000005826 }, "TrainerController.start_learning": { "total": 483.893190564, "count": 1, "self": 0.5604540929968493, "children": { "TrainerController._reset_env": { "total": 8.879436270000014, "count": 1, "self": 8.879436270000014 }, "TrainerController.advance": { "total": 474.3711476930032, "count": 18199, "self": 0.2723188820025939, "children": { "env_step": { "total": 474.0988288110006, "count": 18199, "self": 326.0464686699927, "children": { "SubprocessEnvManager._take_step": { "total": 147.76062719800746, "count": 18199, "self": 1.4799179220131577, "children": { "TorchPolicy.evaluate": { "total": 146.2807092759943, "count": 18199, "self": 146.2807092759943 } } }, "workers": { "total": 0.29173294300045427, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 482.3403618349974, "count": 18199, "is_parallel": true, "self": 234.85654759000155, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005588203000002068, "count": 1, "is_parallel": true, "self": 0.003461074999961511, "children": { "_process_rank_one_or_two_observation": { "total": 0.002127128000040557, "count": 10, "is_parallel": true, "self": 0.002127128000040557 } } }, "UnityEnvironment.step": { "total": 0.05097192599998834, "count": 1, "is_parallel": true, "self": 0.0006522129999382287, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040074900002196046, "count": 1, "is_parallel": true, "self": 0.00040074900002196046 }, "communicator.exchange": { "total": 0.04797621800000229, "count": 1, "is_parallel": true, "self": 0.04797621800000229 }, "steps_from_proto": { "total": 0.0019427460000258634, "count": 1, "is_parallel": true, "self": 0.00040637399996512613, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015363720000607373, "count": 10, "is_parallel": true, "self": 0.0015363720000607373 } } } } } } }, "UnityEnvironment.step": { "total": 247.48381424499584, "count": 18198, "is_parallel": true, "self": 10.954997276993822, "children": { "UnityEnvironment._generate_step_input": { "total": 5.478658276002534, "count": 18198, "is_parallel": true, "self": 5.478658276002534 }, "communicator.exchange": { "total": 196.19229661900064, "count": 18198, "is_parallel": true, "self": 196.19229661900064 }, "steps_from_proto": { "total": 34.85786207299884, "count": 18198, "is_parallel": true, "self": 6.768261388008426, "children": { "_process_rank_one_or_two_observation": { "total": 28.089600684990415, "count": 181980, "is_parallel": true, "self": 28.089600684990415 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.449999996973929e-05, "count": 1, "self": 3.449999996973929e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 470.37357494701087, "count": 516067, "is_parallel": true, "self": 10.509443837031995, "children": { "process_trajectory": { "total": 263.3657390479792, "count": 516067, "is_parallel": true, "self": 262.7419635779792, "children": { "RLTrainer._checkpoint": { "total": 0.6237754699999982, "count": 4, "is_parallel": true, "self": 0.6237754699999982 } } }, "_update_policy": { "total": 196.49839206199965, "count": 90, "is_parallel": true, "self": 64.18866591699796, "children": { "TorchPPOOptimizer.update": { "total": 132.3097261450017, "count": 4587, "is_parallel": true, "self": 132.3097261450017 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08211800799995217, "count": 1, "self": 0.0008280799999056399, "children": { "RLTrainer._checkpoint": { "total": 0.08128992800004653, "count": 1, "self": 0.08128992800004653 } } } } } } }