{"id":"W1506389236","doi":"10.1109/ccece.2015.7129466","title":"An estimation based allocation rule with super-linear regret and finite lock-on time for time-dependent multi-armed bandit processes","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regret; Mathematical optimization; Index (typography); Markov decision process; Multi-armed bandit; Computer science; Upper and lower bounds; Process (computing); Moving average; Markov chain; Markov process; Mathematics; Statistics; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.006882399,0.001459466,0.003579739,0.0009662837,0.0008219296,0.003186604,0.0026426,0.002735135,0.003296612],"category_scores_gemma":[0.02239319,0.0009039672,0.001028772,0.001135288,0.002319738,0.002806991,0.002190335,0.004173783,0.0008801579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00173423,"about_ca_system_score_gemma":0.002231788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003166774,"about_ca_topic_score_gemma":0.002317274,"domain_scores_codex":[0.9960134,0.001592161,0.0002523861,0.0008399095,0.0008163538,0.0004857878],"domain_scores_gemma":[0.9822713,0.01342033,0.001679571,0.0007300761,0.001305527,0.0005931846],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003081462,0.0001632382,0.0009272219,0.0001655998,0.0001004728,0.0001931834,0.0001646855,0.8769278,0.001401644,0.06944644,0.001865944,0.04833576],"study_design_scores_gemma":[0.00001868238,0.0000420998,0.00008562204,0.00002076435,0.00001336238,0.00002482512,0.000006594383,0.9870371,0.0003066711,0.01218384,0.0002477646,0.00001262029],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01667076,0.0007148829,0.9791399,0.0004332388,0.00006698737,0.00007028723,0.00005567707,0.0002487217,0.00259956],"genre_scores_gemma":[0.8346609,0.0009798912,0.1568794,0.0005590087,0.0002366112,0.0003178853,0.0002040064,0.0001815343,0.00598071],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006882399,"threshold_uncertainty_score":0.03639805,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1270840519725417,"score_gpt":0.4245114426048841,"score_spread":0.2974273906323425,"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."}}