{"id":"W2281341692","doi":"10.48550/arxiv.1602.07905","title":"Thompson Sampling is Asymptotically Optimal in General Environments","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Sampling (signal processing); Asymptotically optimal algorithm; Mathematics; Mathematical economics; Applied mathematics; Computer science; Geography; Environmental science; Statistics; Mathematical optimization; Telecommunications","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001506311,0.0004159776,0.0006173143,0.0008392896,0.0001593792,0.0001890953,0.002582197,0.00048999,0.001545846],"category_scores_gemma":[0.0006878506,0.00036005,0.0002992499,0.0007389629,0.0003905327,0.0004740711,0.003427259,0.0009958113,0.001414388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006661649,"about_ca_system_score_gemma":0.0002224422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003244385,"about_ca_topic_score_gemma":0.00001853096,"domain_scores_codex":[0.99527,0.0003699165,0.0005832934,0.002131412,0.0008324434,0.0008129711],"domain_scores_gemma":[0.9966053,0.000950049,0.0003268051,0.001641552,0.0001381603,0.0003380778],"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":[0.0003149321,0.0002725765,0.03277588,0.00001867017,0.0001029683,0.0008975122,0.0003390925,0.9457955,0.0005149752,0.006735114,0.0006312588,0.01160153],"study_design_scores_gemma":[0.002671969,0.0001617106,0.04828326,0.0002338633,0.00005029373,0.0000102362,0.0003654016,0.554428,0.001022952,0.3772286,0.01400113,0.001542631],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3765661,0.00003859233,0.6204466,0.0002636944,0.000371525,0.0003283225,0.00009085971,0.00003512476,0.001859183],"genre_scores_gemma":[0.9737153,0.0002098281,0.004320559,0.00009397536,0.0002144707,0.000001964632,0.00001069413,0.00003887026,0.02139434],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6161261,"threshold_uncertainty_score":0.9998851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2727705402762734,"score_gpt":0.3244993651873518,"score_spread":0.05172882491107839,"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."}}