{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9699838161468506, "min": 0.9699838161468506, "max": 2.872222661972046, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9304.0849609375, "min": 9304.0849609375, "max": 29446.02734375, "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": 12.97990894317627, "min": 0.3812831938266754, "max": 13.012848854064941, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2531.082275390625, "min": 73.96894073486328, "max": 2654.62109375, "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": 0.06987307209280569, "min": 0.06310927961977522, "max": 0.07485789516720295, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27949228837122275, "min": 0.2524371184791009, "max": 0.3646052831078551, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1902139256251793, "min": 0.1142068327594019, "max": 0.28664275025035824, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7608557025007172, "min": 0.4568273310376076, "max": 1.3899727624421025, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.347009730600001e-05, "min": 1.347009730600001e-05, "max": 0.00048647000270600005, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 5.388038922400004e-05, "min": 5.388038922400004e-05, "max": 0.00230860003828, "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": 25.25, "min": 3.590909090909091, "max": 25.836363636363636, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1111.0, "min": 158.0, "max": 1421.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.25, "min": 3.590909090909091, "max": 25.836363636363636, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1111.0, "min": 158.0, "max": 1421.0, "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": "1730964810", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1730965417" }, "total": 606.515037178, "count": 1, "self": 0.5791858499999307, "children": { "run_training.setup": { "total": 0.07194894099995963, "count": 1, "self": 0.07194894099995963 }, "TrainerController.start_learning": { "total": 605.863902387, "count": 1, "self": 0.8719104330004939, "children": { "TrainerController._reset_env": { "total": 6.353950586999986, "count": 1, "self": 6.353950586999986 }, "TrainerController.advance": { "total": 598.5524749329996, "count": 18204, "self": 0.44079491400793813, "children": { "env_step": { "total": 598.1116800189917, "count": 18204, "self": 460.5285866319929, "children": { "SubprocessEnvManager._take_step": { "total": 137.1722062080006, "count": 18204, "self": 2.460940305002339, "children": { "TorchPolicy.evaluate": { "total": 134.71126590299826, "count": 18204, "self": 134.71126590299826 } } }, "workers": { "total": 0.41088717899822313, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 603.8692599249997, "count": 18204, "is_parallel": true, "self": 288.678596038006, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026498940000010407, "count": 1, "is_parallel": true, "self": 0.0008113430000662447, "children": { "_process_rank_one_or_two_observation": { "total": 0.001838550999934796, "count": 10, "is_parallel": true, "self": 0.001838550999934796 } } }, "UnityEnvironment.step": { "total": 0.04435041200002843, "count": 1, "is_parallel": true, "self": 0.0009761590000039178, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047568899998395864, "count": 1, "is_parallel": true, "self": 0.00047568899998395864 }, "communicator.exchange": { "total": 0.04054071900003464, "count": 1, "is_parallel": true, "self": 0.04054071900003464 }, "steps_from_proto": { "total": 0.0023578450000059092, "count": 1, "is_parallel": true, "self": 0.0004575180000756518, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019003269999302574, "count": 10, "is_parallel": true, "self": 0.0019003269999302574 } } } } } } }, "UnityEnvironment.step": { "total": 315.1906638869937, "count": 18203, "is_parallel": true, "self": 15.043272027000967, "children": { "UnityEnvironment._generate_step_input": { "total": 7.6687072699937175, "count": 18203, "is_parallel": true, "self": 7.6687072699937175 }, "communicator.exchange": { "total": 247.69030748400172, "count": 18203, "is_parallel": true, "self": 247.69030748400172 }, "steps_from_proto": { "total": 44.78837710599731, "count": 18203, "is_parallel": true, "self": 9.283642563983506, "children": { "_process_rank_one_or_two_observation": { "total": 35.50473454201381, "count": 182030, "is_parallel": true, "self": 35.50473454201381 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016232999996645958, "count": 1, "self": 0.00016232999996645958, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 591.7496217469978, "count": 793256, "is_parallel": true, "self": 17.596911781010363, "children": { "process_trajectory": { "total": 318.50863661598714, "count": 793256, "is_parallel": true, "self": 317.3355248529871, "children": { "RLTrainer._checkpoint": { "total": 1.1731117630000654, "count": 4, "is_parallel": true, "self": 1.1731117630000654 } } }, "_update_policy": { "total": 255.64407335000027, "count": 90, "is_parallel": true, "self": 72.63145363799862, "children": { "TorchPPOOptimizer.update": { "total": 183.01261971200165, "count": 4587, "is_parallel": true, "self": 183.01261971200165 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0854041039999629, "count": 1, "self": 0.0012824770000179342, "children": { "RLTrainer._checkpoint": { "total": 0.08412162699994497, "count": 1, "self": 0.08412162699994497 } } } } } } }