{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6785414814949036, "min": 0.6424476504325867, "max": 2.6115665435791016, "count": 40 }, "SnowballTarget.Policy.Entropy.sum": { "value": 34311.80859375, "min": 32338.24609375, "max": 132288.90625, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 50347.0, "min": 48158.0, "max": 50347.0, "count": 40 }, "SnowballTarget.Step.mean": { "value": 1999800.0, "min": 49800.0, "max": 1999800.0, "count": 40 }, "SnowballTarget.Step.sum": { "value": 1999800.0, "min": 49800.0, "max": 1999800.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.278741836547852, "min": 2.7476751804351807, "max": 14.278741836547852, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 3569.685546875, "min": 684.171142578125, "max": 3569.685546875, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.912, "min": 8.74698795180723, "max": 27.96, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 6978.0, "min": 2178.0, "max": 6990.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.912, "min": 8.74698795180723, "max": 27.96, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 6978.0, "min": 2178.0, "max": 6990.0, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06906834343111276, "min": 0.06544568895404314, "max": 0.07201989505295396, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 1.5885718989155935, "min": 1.469503760910205, "max": 1.6564575862179411, "count": 40 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17110422421294402, "min": 0.16093404756863708, "max": 0.2658214076070428, "count": 40 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 3.9353971568977126, "min": 3.5891555321275024, "max": 6.113892374961985, "count": 40 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.660098780000001e-06, "min": 3.660098780000001e-06, "max": 0.00029620500126499995, "count": 40 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 8.418227194000002e-05, "min": 8.418227194000002e-05, "max": 0.006641940086019998, "count": 40 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10121999999999999, "min": 0.10121999999999999, "max": 0.19873500000000002, "count": 40 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 2.32806, "min": 2.32806, "max": 4.51398, "count": 40 }, "SnowballTarget.Policy.Beta.mean": { "value": 7.087800000000001e-05, "min": 7.087800000000001e-05, "max": 0.0049368765, "count": 40 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0016301940000000002, "min": 0.0016301940000000002, "max": 0.110707602, "count": 40 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1691695202", "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": "1691699793" }, "total": 4591.0157084269995, "count": 1, "self": 0.44240913599969645, "children": { "run_training.setup": { "total": 0.05131418900009521, "count": 1, "self": 0.05131418900009521 }, "TrainerController.start_learning": { "total": 4590.521985102, "count": 1, "self": 6.276178060033089, "children": { "TrainerController._reset_env": { "total": 5.622686312000042, "count": 1, "self": 5.622686312000042 }, "TrainerController.advance": { "total": 4578.469465813968, "count": 182006, "self": 2.928213151115415, "children": { "env_step": { "total": 4575.5412526628525, "count": 182006, "self": 3154.6029376747974, "children": { "SubprocessEnvManager._take_step": { "total": 1417.944118609099, "count": 182006, "self": 17.412136815113172, "children": { "TorchPolicy.evaluate": { "total": 1400.5319817939858, "count": 182006, "self": 1400.5319817939858 } } }, "workers": { "total": 2.9941963789558486, "count": 182006, "self": 0.0, "children": { "worker_root": { "total": 4575.293590029838, "count": 182006, "is_parallel": true, "self": 1996.0307432919021, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006735440000056769, "count": 1, "is_parallel": true, "self": 0.004277886000181752, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024575539998750173, "count": 10, "is_parallel": true, "self": 0.0024575539998750173 } } }, "UnityEnvironment.step": { "total": 0.04643667799996365, "count": 1, "is_parallel": true, "self": 0.00071803399964665, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004220640000767162, "count": 1, "is_parallel": true, "self": 0.0004220640000767162 }, "communicator.exchange": { "total": 0.043091978000120434, "count": 1, "is_parallel": true, "self": 0.043091978000120434 }, "steps_from_proto": { "total": 0.0022046020001198485, "count": 1, "is_parallel": true, "self": 0.0004937830001381371, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017108189999817114, "count": 10, "is_parallel": true, "self": 0.0017108189999817114 } } } } } } }, "UnityEnvironment.step": { "total": 2579.262846737936, "count": 182005, "is_parallel": true, "self": 107.03930975787944, "children": { "UnityEnvironment._generate_step_input": { "total": 53.537830163208355, "count": 182005, "is_parallel": true, "self": 53.537830163208355 }, "communicator.exchange": { "total": 2057.1092542659258, "count": 182005, "is_parallel": true, "self": 2057.1092542659258 }, "steps_from_proto": { "total": 361.5764525509219, "count": 182005, "is_parallel": true, "self": 66.50220276576465, "children": { "_process_rank_one_or_two_observation": { "total": 295.07424978515724, "count": 1820050, "is_parallel": true, "self": 295.07424978515724 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0016382239991798997, "count": 1, "self": 0.0016382239991798997, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 4562.398264727291, "count": 2420466, "is_parallel": true, "self": 54.8306880113505, "children": { "process_trajectory": { "total": 1529.8540156969339, "count": 2420466, "is_parallel": true, "self": 1516.8802767409325, "children": { "RLTrainer._checkpoint": { "total": 12.973738956001398, "count": 40, "is_parallel": true, "self": 12.973738956001398 } } }, "_update_policy": { "total": 2977.713561019006, "count": 909, "is_parallel": true, "self": 966.5060936679658, "children": { "TorchPPOOptimizer.update": { "total": 2011.2074673510403, "count": 46359, "is_parallel": true, "self": 2011.2074673510403 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15201669199996104, "count": 1, "self": 0.000976614000137488, "children": { "RLTrainer._checkpoint": { "total": 0.15104007799982355, "count": 1, "self": 0.15104007799982355 } } } } } } }