{"id":"W2970245835","doi":"","title":"Learning Reliable Policies in the Bandit Setting with Application to Adaptive Clinical Trials.","year":2019,"lang":"en","type":"article","venue":"International Joint Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning","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":[0.04679241,0.001707726,0.004506533,0.001639951,0.0008381659,0.003279308,0.002440714,0.003853618,0.003852237],"category_scores_gemma":[0.1770536,0.001350672,0.001004755,0.00155119,0.002723547,0.003127042,0.002462611,0.005553229,0.0007538397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001817098,"about_ca_system_score_gemma":0.003673457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004966278,"about_ca_topic_score_gemma":0.003240473,"domain_scores_codex":[0.9800332,0.01686505,0.0006801006,0.001125501,0.000763146,0.0005330385],"domain_scores_gemma":[0.7877603,0.1981852,0.005720254,0.003376164,0.003242233,0.001715818],"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":[0.002369605,0.0003197922,0.004676634,0.0004501037,0.0004985978,0.0002856993,0.0003040928,0.8491476,0.0003449269,0.04633938,0.003461042,0.09180246],"study_design_scores_gemma":[0.0002593046,0.0001997377,0.0004546626,0.0000738011,0.00007440128,0.00004170156,0.00003703832,0.9530048,0.0002393038,0.04500024,0.0005942747,0.00002063964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04189833,0.003520042,0.9474921,0.00305289,0.0002636751,0.0004597592,0.0002331907,0.0007642297,0.002315717],"genre_scores_gemma":[0.7991498,0.001677715,0.1929982,0.001092011,0.0003245674,0.001232168,0.0003396165,0.0001352538,0.003050728],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04679241,"threshold_uncertainty_score":0.2474648,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4440932873400193,"score_gpt":0.5419922742734516,"score_spread":0.0978989869334323,"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."}}