{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003727403,0.0001249598,0.0004939366,0.0002781165,0.00004118092,0.0001761025,0.000850233,0.00007681394,0.0003120878],"category_scores_gemma":[0.005016549,0.00007920113,0.00009905214,0.0006656022,0.0002023975,0.0003619574,0.0001113579,0.0001212408,0.0003846546],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004691748,"about_ca_system_score_gemma":0.0001720474,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001124969,"about_ca_topic_score_gemma":0.000004558508,"domain_scores_codex":[0.9957029,0.0003577951,0.0007429768,0.0003862332,0.002459508,0.0003505447],"domain_scores_gemma":[0.9962168,0.001547811,0.000213428,0.0007142024,0.0009750617,0.000332668],"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":[0.004867009,0.001135375,0.02129203,0.0000694036,0.0004647146,0.0003873436,0.002648357,0.6755677,0.01275881,0.01226915,0.09579182,0.1727482],"study_design_scores_gemma":[0.004761575,0.0005996744,0.0006793507,0.00001407951,0.00001002019,0.00002675256,0.002626889,0.9548072,0.00207876,0.006833715,0.02729191,0.0002700501],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01492827,0.0001918932,0.9784997,0.0002629256,0.0003977434,0.0003708122,0.00002711295,0.00004400801,0.005277553],"genre_scores_gemma":[0.9803636,0.000001667145,0.01362269,0.000035505,0.00007396101,0.00002422901,0.000001240711,0.00001169937,0.005865404],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9654353,"threshold_uncertainty_score":0.6005641,"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."}}