{"id":"W2071814471","doi":"10.1145/1102351.1102472","title":"Bayesian sparse sampling for on-line reward optimization","year":2005,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":122,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Machine learning; Bayesian probability; Sampling (signal processing); Action selection; Artificial intelligence; Bayesian optimization; Thompson sampling; Selection (genetic algorithm); Bayesian inference; Mathematical optimization; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0002044868,0.00009482022,0.00008949183,0.00007857605,0.0001050655,0.0001308462,0.0004051294,0.00004316707,0.00006110704],"category_scores_gemma":[0.00009804495,0.00008619505,0.00004400756,0.0001499227,0.00001064408,0.0002995117,0.00007143758,0.0000667901,0.00006296292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004771127,"about_ca_system_score_gemma":0.00002682212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001802917,"about_ca_topic_score_gemma":0.000001253765,"domain_scores_codex":[0.9991587,0.00001248374,0.0001999891,0.0002349048,0.0001751883,0.0002187774],"domain_scores_gemma":[0.9993139,0.0001159356,0.00006806522,0.0003744966,0.00006703535,0.00006054727],"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":[0.000003834301,0.00001156692,0.00001825008,0.000003535171,0.000004326756,1.763519e-7,0.00006200455,0.9643478,0.000008761928,0.02522848,0.0006753528,0.009635856],"study_design_scores_gemma":[0.0002683043,0.0001354999,0.000007431322,0.00001067884,0.000002603,0.000001294456,0.000004501995,0.9839454,0.0004338111,0.0001171383,0.01496264,0.0001107329],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002225471,0.000004492104,0.9897553,0.00252706,0.0001919579,0.0002053299,2.935994e-7,0.0002393114,0.007054018],"genre_scores_gemma":[0.07929439,0.000005886845,0.9159237,0.001270934,0.0001748693,0.0000105669,0.000007168548,0.00001035927,0.00330213],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.07927214,"threshold_uncertainty_score":0.3514932,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06390024574608347,"score_gpt":0.3090228942151267,"score_spread":0.2451226484690433,"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."}}