{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003527156,0.0004244393,0.0005493574,0.001434095,0.0004400422,0.0008503917,0.002176995,0.0002168314,0.0002632183],"category_scores_gemma":[0.00119875,0.0002913814,0.00008569844,0.0009793263,0.001009993,0.0007764098,0.0007108473,0.00113327,0.0002669151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003236222,"about_ca_system_score_gemma":0.0004590205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001043138,"about_ca_topic_score_gemma":0.0001080186,"domain_scores_codex":[0.992259,0.00008657784,0.0007205807,0.001569565,0.004700533,0.000663777],"domain_scores_gemma":[0.9956976,0.001629531,0.0004653451,0.001199797,0.0007927124,0.0002150106],"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":[0.00001292038,0.000002471627,0.0000257344,0.000003413029,0.000002467037,0.00002013568,0.0002452241,0.5817076,0.000009550692,0.0004723723,0.00001308193,0.4174851],"study_design_scores_gemma":[0.0002775916,0.0005022202,0.0000241116,0.0001775894,0.000003459296,0.00002344599,0.00000142829,0.8576295,0.0004938569,0.1290526,0.01138206,0.0004320537],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00001226918,0.00005389135,0.9932496,0.0005718725,0.0004718661,0.0004015226,8.285688e-7,0.00006517885,0.005172972],"genre_scores_gemma":[0.6627947,0.00006120461,0.3125417,0.0009164478,0.00149509,0.00003962478,0.00002163995,0.0001136663,0.02201591],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6807079,"threshold_uncertainty_score":0.9999538,"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."}}