{"id":"W4289655140","doi":"10.1109/isit50566.2022.9834636","title":"Multi-Environment Meta-Learning in Stochastic Linear Bandits","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Symposium on Information Theory (ISIT)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Regret; Task (project management); Computer science; Artificial intelligence; Meta learning (computer science); Machine learning; Multi-task learning; Task analysis; 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":[0.00618944,0.002007401,0.003531234,0.0008857719,0.000911599,0.002699723,0.002926289,0.003633302,0.002042148],"category_scores_gemma":[0.01817562,0.001324839,0.001238117,0.001198428,0.002884987,0.004279771,0.002876553,0.004069193,0.0005471887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002223955,"about_ca_system_score_gemma":0.001374267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002506974,"about_ca_topic_score_gemma":0.002303154,"domain_scores_codex":[0.9967464,0.001903877,0.0001237271,0.000550438,0.0003237636,0.0003517557],"domain_scores_gemma":[0.9880711,0.009467433,0.000951916,0.0006011109,0.0005318237,0.0003765978],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000105479,0.00005628862,0.0005212307,0.0000613752,0.00007725668,0.00005668565,0.00005632804,0.9560602,0.0002360202,0.03303545,0.0004638943,0.009269807],"study_design_scores_gemma":[0.00001160484,0.00002289708,0.00003721464,0.00001072151,0.000007605253,0.000009146293,0.000007056742,0.9798332,0.00009918142,0.01983296,0.0001222808,0.00000617585],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02498942,0.0008401221,0.9712645,0.000731147,0.00005338442,0.00005200211,0.00006580482,0.0002481848,0.001755411],"genre_scores_gemma":[0.8671146,0.0005893109,0.1264256,0.00057146,0.000209546,0.0003857344,0.0001762109,0.0001516538,0.00437603],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00618944,"threshold_uncertainty_score":0.03273326,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0688220592948622,"score_gpt":0.3667842287866565,"score_spread":0.2979621694917943,"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."}}