{"id":"W1915057100","doi":"10.1007/978-3-319-11662-4_13","title":"Bayesian Reinforcement Learning with Exploration","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"Reinforcement learning; Computer science; Minimax; Sample complexity; Bayesian probability; Class (philosophy); Artificial intelligence; Sample (material); Machine learning; Mathematical optimization; Mathematics","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":[0.0009557473,0.0007787569,0.0008052648,0.0003308645,0.0002606023,0.0009595681,0.0009706297,0.00103271,0.009379435],"category_scores_gemma":[0.003842843,0.0004143643,0.0004096134,0.0004877076,0.0008005434,0.001188448,0.001316543,0.001948794,0.001720053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006083237,"about_ca_system_score_gemma":0.0006142547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009488658,"about_ca_topic_score_gemma":0.001134642,"domain_scores_codex":[0.999549,0.0001818435,0.00001592489,0.00007941557,0.0001380797,0.00003569174],"domain_scores_gemma":[0.9991364,0.0006099384,0.00004229866,0.00008407466,0.00008450045,0.00004289762],"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":[0.0001041559,0.00008819831,0.0002888395,0.0001523076,0.00005774084,0.0000559095,0.00007004421,0.4447542,0.001306476,0.2554016,0.01265388,0.2850667],"study_design_scores_gemma":[0.00001941563,0.00003479699,0.0000894896,0.00003094853,0.00001092772,0.00003505198,0.000006277957,0.8056175,0.0004863883,0.1875809,0.006076556,0.00001170224],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00422211,0.00151426,0.9637949,0.0005569445,0.0001866429,0.00002836606,0.00005138347,0.0003590698,0.02928638],"genre_scores_gemma":[0.5483428,0.002602946,0.3572809,0.0004719336,0.0005080724,0.0003277023,0.0002675171,0.0003742274,0.08982392],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009379435,"threshold_uncertainty_score":0.03137738,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06435445389814211,"score_gpt":0.3528636545911634,"score_spread":0.2885092006930213,"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."}}