{"id":"W2911952628","doi":"10.1109/tac.2019.2895253","title":"Thompson Sampling for Stochastic Control: The Continuous Parameter Case","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Automatic Control","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sampling (signal processing); Regret; Stochastic control; Mathematics; Control (management); Mathematical optimization; State (computer science); Class (philosophy); Thompson sampling; Computer science; Applied mathematics; Control theory (sociology); Optimal control; Statistics; Algorithm; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002897863,0.0003232273,0.0007566158,0.0003602495,0.0005924528,0.0004378768,0.000760322,0.0001363996,0.00122146],"category_scores_gemma":[0.001136204,0.0001970353,0.0004750825,0.0005466171,0.0001844498,0.0003186432,0.000002658907,0.0003832758,0.0009257573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001166436,"about_ca_system_score_gemma":0.0001246342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002169714,"about_ca_topic_score_gemma":0.0000639499,"domain_scores_codex":[0.9958439,0.0004141783,0.000959991,0.000697537,0.001379157,0.0007051716],"domain_scores_gemma":[0.9688218,0.02903291,0.0002964546,0.001187994,0.0004791225,0.0001817537],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005245343,0.0002521479,0.00001291035,0.00002345481,0.0002724234,0.00006156402,0.0005662738,0.4607887,0.0006755481,0.00006895396,0.0002418651,0.5365116],"study_design_scores_gemma":[0.006154603,0.0004405073,0.00007746379,0.00003301128,0.0001151675,0.0003626335,0.0007458288,0.9876035,0.0001822781,0.003280432,0.0007492211,0.0002553783],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03558693,0.00005273363,0.9572486,0.001634922,0.001328046,0.003653913,0.0002684323,0.0001776229,0.00004877672],"genre_scores_gemma":[0.993169,9.915666e-7,0.003444151,0.0005963324,0.00009280886,0.0007677448,8.610136e-7,0.00004616329,0.001882011],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.957582,"threshold_uncertainty_score":0.9998521,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07199831115677265,"score_gpt":0.3889426739652809,"score_spread":0.3169443628085083,"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."}}