{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002740645,0.001018791,0.00122915,0.0004750924,0.0003840626,0.0005773473,0.001462708,0.0009170736,0.001296679],"category_scores_gemma":[0.01413012,0.0005186126,0.0004336054,0.0003030771,0.001376178,0.001323453,0.001563986,0.001671545,0.0002706017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009917826,"about_ca_system_score_gemma":0.001053849,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003580585,"about_ca_topic_score_gemma":0.00309307,"domain_scores_codex":[0.9989344,0.0004176048,0.00005098555,0.0002183601,0.0002393381,0.000139241],"domain_scores_gemma":[0.994386,0.00370237,0.0006781843,0.0004261624,0.0005339982,0.0002733204],"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":[0.0001821529,0.0001072279,0.001212281,0.00006794433,0.00005250412,0.00006165082,0.00006414192,0.9517629,0.002742014,0.008987189,0.0007607297,0.03399921],"study_design_scores_gemma":[0.00001517418,0.00005192189,0.00007984147,0.000003702565,0.000003833279,0.00001141037,0.000003177127,0.9954085,0.0003245255,0.00400566,0.00008821049,0.000003989835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08854472,0.000331498,0.9072031,0.0004166105,0.00004962408,0.00007472732,0.00005181702,0.0007230587,0.002604841],"genre_scores_gemma":[0.9532633,0.00009415249,0.04503148,0.0002314821,0.00003578858,0.00008468251,0.00006384647,0.00006766304,0.001127519],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003580585,"threshold_uncertainty_score":0.01449412,"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."}}