{"id":"W2914526782","doi":"10.48550/arxiv.1602.04282","title":"Conservative Bandits","year":2016,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Mathematical optimization; Constraint (computer-aided design); Complement (music); Computer science; Revenue; Baseline (sea); Adversarial system; Upper and lower bounds; Mathematical economics; Mathematics; Economics; Artificial intelligence; Machine learning; Finance","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":[0.003059483,0.001363121,0.002180307,0.000787251,0.0009808943,0.002735463,0.002252403,0.003044228,0.006186027],"category_scores_gemma":[0.01585959,0.000701408,0.000980634,0.001270749,0.002386773,0.003414135,0.001981128,0.002976416,0.001015242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001571941,"about_ca_system_score_gemma":0.001024796,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001624525,"about_ca_topic_score_gemma":0.001528353,"domain_scores_codex":[0.9977173,0.00107014,0.00009505911,0.0004561667,0.0003550588,0.000306361],"domain_scores_gemma":[0.9908337,0.006997415,0.0009568077,0.0005802568,0.0003029745,0.0003288287],"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":[0.0003529397,0.0001481681,0.001213454,0.0001999726,0.0000956994,0.0002591923,0.0001659887,0.7197962,0.001361916,0.2501385,0.004700556,0.02156737],"study_design_scores_gemma":[0.00004996673,0.00006643098,0.0001255903,0.00003186971,0.00001622293,0.00005276607,0.00002511316,0.8904901,0.0002761645,0.1073249,0.001528008,0.00001297441],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08008899,0.001155301,0.8946264,0.00188567,0.0002039494,0.0001685583,0.0004463258,0.0003855705,0.0210392],"genre_scores_gemma":[0.8962048,0.0008690025,0.08592413,0.0006849868,0.000258479,0.0004235469,0.000440066,0.0001395438,0.01505542],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006186027,"threshold_uncertainty_score":0.02069438,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3343304838033287,"score_gpt":0.3034758773787182,"score_spread":0.03085460642461052,"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."}}