{"id":"W2024490033","doi":"10.1007/s001860300295","title":"One-armed bandit models with continuous and delayed responses","year":2003,"lang":"en","type":"article","venue":"Mathematical Methods of Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan; University of Manitoba","funders":"","keywords":"Multi-armed bandit; Monotonic function; Markov decision process; Sequence (biology); Optimal stopping; Markov process; Mathematical optimization; Limit (mathematics); Index (typography); Bayesian probability; Markov chain; Mathematics; Time horizon; Computer science; Statistics","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":[0.01334829,0.003820112,0.007636277,0.001823144,0.001360618,0.00725312,0.005388073,0.009102272,0.008731729],"category_scores_gemma":[0.04281554,0.002430972,0.002286056,0.002962945,0.005125827,0.007060435,0.003255745,0.005994548,0.002449199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002422548,"about_ca_system_score_gemma":0.001336567,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005899195,"about_ca_topic_score_gemma":0.003891337,"domain_scores_codex":[0.9920358,0.004626859,0.0003759732,0.001406976,0.0004922775,0.001062166],"domain_scores_gemma":[0.9318902,0.05793292,0.005233355,0.002204049,0.00193357,0.0008060219],"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":[0.0007072025,0.000187655,0.001644849,0.0002360479,0.0002870785,0.0002993444,0.0002064036,0.8491155,0.0002836902,0.1373985,0.001573299,0.008060481],"study_design_scores_gemma":[0.0001297854,0.00009363299,0.0002462106,0.00003433047,0.00009309856,0.00003867071,0.00005496741,0.9436342,0.0001422702,0.05510551,0.000378759,0.00004850695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1220695,0.002587455,0.8621768,0.003173064,0.0003921879,0.0002842402,0.001239593,0.0005759908,0.007501136],"genre_scores_gemma":[0.9274741,0.00213276,0.04058844,0.000604392,0.0005329564,0.0008393444,0.0008126536,0.00008760778,0.02692783],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01334829,"threshold_uncertainty_score":0.07059336,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5018446804662678,"score_gpt":0.6032521031918505,"score_spread":0.1014074227255827,"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."}}