{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002160389,0.000218259,0.000285913,0.000345301,0.0001917389,0.000301524,0.0004317243,0.0001021489,0.0002885571],"category_scores_gemma":[0.006087448,0.0001402157,0.00002670437,0.0006177689,0.0001558204,0.001017546,0.0000446025,0.0001212448,0.0006159999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008701628,"about_ca_system_score_gemma":0.0004448487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002299391,"about_ca_topic_score_gemma":0.00005559695,"domain_scores_codex":[0.9966443,0.0001492309,0.0004097923,0.0007238566,0.001726158,0.0003466723],"domain_scores_gemma":[0.9953917,0.00186199,0.0001491047,0.0005575663,0.001707246,0.0003323865],"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":[0.002983557,0.001142229,0.001894098,0.0000988696,0.00004549387,0.00002142906,0.001284376,0.8903508,0.001926015,0.00003691694,0.004298699,0.09591758],"study_design_scores_gemma":[0.002686878,0.001139814,0.0002723072,0.00002714421,0.00001007425,0.000005133391,0.0002190486,0.9799299,0.01340671,0.001363614,0.0007157273,0.0002236852],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.035989,0.00003788762,0.9618302,0.0006974727,0.00003995917,0.001037523,0.00006973658,0.0001287988,0.0001694119],"genre_scores_gemma":[0.7270252,0.00000512364,0.2593455,0.0002634347,0.0001380689,0.0002541542,0.0003137676,0.00006477688,0.01259002],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7024847,"threshold_uncertainty_score":0.7917638,"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."}}