{"id":"W4206530644","doi":"10.1017/9781108571401","title":"Bandit Algorithms","year":2020,"lang":"en","type":"book","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":851,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Markov decision process; Intuition; Mathematical proof; Bayesian probability; Thompson sampling; Artificial intelligence; Focus (optics); Machine learning; Operations research; Markov process; Management science; Mathematical optimization; Mathematics; Engineering","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":[0.00237404,0.002028273,0.002544644,0.001326196,0.001219177,0.004599835,0.002734886,0.002845929,0.02660274],"category_scores_gemma":[0.01250982,0.0007751642,0.001316275,0.00270307,0.001527657,0.003189528,0.002703371,0.00341242,0.011547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001766057,"about_ca_system_score_gemma":0.001823009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00268368,"about_ca_topic_score_gemma":0.002809577,"domain_scores_codex":[0.9978431,0.000880294,0.0001354788,0.0004009207,0.0005304456,0.000209685],"domain_scores_gemma":[0.995665,0.003020458,0.0002306295,0.0005434608,0.0004289734,0.0001114773],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001656871,0.000130587,0.0006630686,0.0004299123,0.0001824412,0.00008686222,0.0001206394,0.2127413,0.0006515872,0.425747,0.04053511,0.3185458],"study_design_scores_gemma":[0.00005611701,0.00005667646,0.0001780738,0.0001882982,0.00004929845,0.0001078681,0.00004729583,0.5465144,0.0005025584,0.4187463,0.03352221,0.00003102887],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003189385,0.006442642,0.936176,0.001613355,0.0005806654,0.0001671609,0.000487539,0.001035741,0.05030755],"genre_scores_gemma":[0.2023543,0.01442132,0.6748054,0.002450048,0.001267659,0.001253412,0.002198085,0.001134496,0.1001153],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02660274,"threshold_uncertainty_score":0.08899504,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1148289934412215,"score_gpt":0.330816909380413,"score_spread":0.2159879159391914,"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."}}