{"id":"W2809048072","doi":"10.1002/asmb.2355","title":"A Bayesian two‐armed bandit model","year":2018,"lang":"en","type":"article","venue":"Applied Stochastic Models in Business and Industry","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Stochastic game; Monotonic function; Mathematical optimization; Multi-armed bandit; Dynamic programming; Computer science; Bayesian probability; Outcome (game theory); Value (mathematics); Term (time); Sequence (biology); Stochastic programming; Mathematical economics; Economics; Mathematics; Artificial intelligence; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001286064,0.0003075599,0.0004961345,0.0005844543,0.0002849272,0.0002449585,0.0007459084,0.0004314331,0.0002651907],"category_scores_gemma":[0.0005419644,0.0002462768,0.00003426546,0.001854635,0.0007403991,0.00054237,0.0004478958,0.0008204002,0.00006266899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007774447,"about_ca_system_score_gemma":0.0002592792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000721394,"about_ca_topic_score_gemma":0.00006990269,"domain_scores_codex":[0.996143,0.00004441514,0.0007022817,0.000977546,0.001417956,0.0007148284],"domain_scores_gemma":[0.9978403,0.0004657515,0.0001636674,0.0007424291,0.0005204445,0.0002674303],"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":[0.0001794124,0.00009158714,0.00004803736,0.000007070912,0.000009305966,0.00001133964,0.0005481168,0.9375579,0.0001756474,0.01699002,0.0006944018,0.04368721],"study_design_scores_gemma":[0.001164894,0.0000188815,0.0002832745,0.00002562053,0.000004389803,0.00001024389,0.0002468604,0.7084045,0.00004028249,0.2895364,0.00004502208,0.0002196516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05298108,0.00004544988,0.9391434,0.0004172535,0.000159327,0.0004026267,0.00002083751,0.00004336054,0.006786672],"genre_scores_gemma":[0.9930406,0.00000558692,0.00546069,0.0002108272,0.0003722695,0.0001259521,0.000004958086,0.000035958,0.0007431355],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9400595,"threshold_uncertainty_score":0.9999989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1201796460493762,"score_gpt":0.3928292364248337,"score_spread":0.2726495903754575,"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."}}