{"id":"W7124301226","doi":"10.65109/reoc9270","title":"Boosting Robustness in Preference-Based Reinforcement Learning with Dynamic Sparsity","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Boosting (machine learning); Robustness (evolution); Focus (optics); Artificial neural network; Training set","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001338069,0.0007101485,0.0007208917,0.0009562011,0.0006636734,0.0008643596,0.00189037,0.0002892869,0.0002059776],"category_scores_gemma":[0.0003491637,0.0006759992,0.0001249989,0.002923954,0.0002563961,0.0008797163,0.001075592,0.001613704,0.00005106843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000933214,"about_ca_system_score_gemma":0.001538185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003177943,"about_ca_topic_score_gemma":0.000271885,"domain_scores_codex":[0.9945796,0.0004001898,0.001234323,0.001326804,0.001045346,0.001413713],"domain_scores_gemma":[0.9972013,0.0003916802,0.0005841965,0.001259103,0.0003675029,0.0001962806],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001201446,0.00007463816,0.04210116,0.0003608053,0.00006349678,0.00004373545,0.0003979667,0.9446107,0.00002675506,0.004465562,0.0000251208,0.007709931],"study_design_scores_gemma":[0.00246008,0.0006339377,0.01199319,0.002690621,0.00005605667,0.000003300573,0.0002373789,0.9805359,0.0002943265,0.00002310869,0.0003441181,0.0007279449],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01764418,0.0001183683,0.9426981,0.0008866877,0.0005459133,0.0009859245,1.944185e-7,0.0002996457,0.03682094],"genre_scores_gemma":[0.9446684,0.00004169878,0.02987654,0.0004025008,0.00001666965,0.00003531844,0.00001208433,0.00002771019,0.02491914],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9270242,"threshold_uncertainty_score":0.9995691,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02930018862736242,"score_gpt":0.2480460738424779,"score_spread":0.2187458852151155,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}