{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.006328962,0.000258781,0.0003642829,0.001094376,0.0005255877,0.0002453728,0.001542424,0.00006554343,0.01471577],"category_scores_gemma":[0.001389556,0.000221332,0.0002513188,0.0006948395,0.0000996685,0.001743263,0.0005776795,0.0009747466,0.002607534],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008641634,"about_ca_system_score_gemma":0.00007692537,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001717495,"about_ca_topic_score_gemma":0.000003667128,"domain_scores_codex":[0.9928707,0.0008515951,0.001224363,0.0004484205,0.004215698,0.0003892256],"domain_scores_gemma":[0.9967059,0.001921736,0.0005648921,0.0004720144,0.0002028554,0.0001326024],"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":[0.0003239276,0.0001365536,0.0001014683,0.000001734935,0.0001351368,0.00001086032,0.001483365,0.9904506,0.0002556178,0.001817006,0.0007749851,0.004508755],"study_design_scores_gemma":[0.002468115,0.0004212095,0.001299149,0.000009806412,0.00004843988,0.00004724879,0.00405792,0.8727314,0.000824586,0.009697245,0.1078771,0.0005177107],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04085376,0.00011796,0.9393944,0.00416436,0.004590476,0.001519368,0.0006164659,0.0002240939,0.008519077],"genre_scores_gemma":[0.9854907,0.00002710324,0.0008871653,0.001025339,0.0001809786,0.0006699438,0.0002174926,0.00002980819,0.01147143],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.944637,"threshold_uncertainty_score":0.9981691,"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."}}