{"id":"W2403303158","doi":"","title":"Bayesian optimal control of smoothly parameterized systems","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Parameterized complexity; Markov decision process; Mathematical optimization; Computer science; Thompson sampling; Bayesian probability; Mathematics; Algorithm; Markov process; Artificial intelligence; Machine learning","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":[0.002068276,0.001364115,0.001429611,0.0005867788,0.0004668908,0.001741316,0.001477942,0.00154071,0.002960199],"category_scores_gemma":[0.008810697,0.0006883676,0.0009817212,0.000691301,0.002244627,0.001986619,0.001799823,0.002353063,0.0002598582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002099626,"about_ca_system_score_gemma":0.001323135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008104663,"about_ca_topic_score_gemma":0.003810256,"domain_scores_codex":[0.9988173,0.0004735715,0.00003930734,0.0002637819,0.0002291115,0.0001770068],"domain_scores_gemma":[0.9966037,0.002481732,0.0003848206,0.0001608654,0.0001926746,0.0001761207],"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":[0.00003967703,0.00001794668,0.0001933281,0.00004391583,0.00002394789,0.00004336068,0.00004307476,0.9347686,0.0003809221,0.0597968,0.0003013596,0.004347085],"study_design_scores_gemma":[0.000008597126,0.00001252749,0.00005382184,0.000004888946,0.000003382523,0.000003477106,0.000005458061,0.9770595,0.00007009202,0.02255346,0.0002204346,0.000004359483],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03166996,0.0006245559,0.9610137,0.0006023578,0.00003988952,0.00005200511,0.00009918901,0.000152116,0.005746256],"genre_scores_gemma":[0.9382786,0.0008607085,0.05498702,0.0001638627,0.00008538984,0.0001822533,0.0001462793,0.00007562985,0.005220359],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008104663,"threshold_uncertainty_score":0.01611495,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1825469985388548,"score_gpt":0.4346419930056865,"score_spread":0.2520949944668318,"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."}}