{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007637636,0.001424607,0.002490571,0.0008190399,0.0007381939,0.001905159,0.001907575,0.002304407,0.002397656],"category_scores_gemma":[0.03696666,0.0005569089,0.0009045007,0.001152213,0.002954811,0.002906287,0.001929551,0.002532059,0.0002559728],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001960823,"about_ca_system_score_gemma":0.001664527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004426778,"about_ca_topic_score_gemma":0.00210349,"domain_scores_codex":[0.9956169,0.002372032,0.0001775431,0.0006863436,0.0008363865,0.0003107289],"domain_scores_gemma":[0.9748871,0.02114069,0.001123274,0.001439128,0.0009076902,0.0005022465],"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":[0.0002851101,0.00005606388,0.001067156,0.0001540668,0.0000968635,0.0001776198,0.0001124204,0.7799892,0.001323629,0.1973714,0.0007649519,0.01860162],"study_design_scores_gemma":[0.00001906202,0.00006122652,0.0001781349,0.00002031547,0.000009871363,0.00003044964,0.0000113352,0.9392757,0.0004385706,0.05960006,0.0003430412,0.00001215267],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02649026,0.0009437471,0.969026,0.0004924192,0.00004987804,0.00007093439,0.00006266724,0.000126114,0.002738029],"genre_scores_gemma":[0.8892894,0.001052685,0.1063776,0.0003027745,0.0001541871,0.0002142262,0.0001648351,0.0001073478,0.002337052],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007637636,"threshold_uncertainty_score":0.04039216,"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."}}