{"id":"W2236244207","doi":"10.1561/2200000049","title":"Bayesian Reinforcement Learning: A Survey","year":2015,"lang":"en","type":"article","venue":"Foundations and Trends® in Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":223,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Machine learning; Reinforcement learning; Artificial intelligence; Bayesian inference; Bayesian probability; Variable-order Bayesian network; Prior probability; Inference; Bellman equation; Algorithm; Mathematical optimization; Mathematics","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":[0.001479584,0.0002161315,0.0002320648,0.0006192418,0.0003316178,0.0004510015,0.0004007877,0.00007362461,0.0001070848],"category_scores_gemma":[0.0006175301,0.000215479,0.00004370805,0.001155608,0.00005793959,0.0006242121,0.0003474737,0.0006992697,0.00006496777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001080186,"about_ca_system_score_gemma":0.00006361707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00113169,"about_ca_topic_score_gemma":0.0003716036,"domain_scores_codex":[0.9979447,0.0004275327,0.0004201437,0.0004207795,0.0003861769,0.0004006943],"domain_scores_gemma":[0.9989625,0.0002076822,0.0001983828,0.0003276474,0.0001085285,0.0001952816],"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":[0.000007608463,0.00001615743,0.1566369,0.000004218743,0.00001376265,0.000007336901,0.001010488,0.8160558,0.000002830401,0.005321153,0.00009279529,0.02083096],"study_design_scores_gemma":[0.000790716,0.000207591,0.04959874,0.00001674413,0.000005486397,0.00001307129,0.00006400618,0.9257292,0.000002412519,0.0001554297,0.02317936,0.0002372948],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00440627,0.0001102843,0.9754209,0.0005987748,0.0002232921,0.00009258708,4.754638e-7,0.0002337435,0.0189137],"genre_scores_gemma":[0.9800444,0.00002885283,0.008560605,0.00006780464,0.00003635856,0.00001436065,0.0002063629,0.00001953804,0.01102169],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9756382,"threshold_uncertainty_score":0.8786981,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0465390705497981,"score_gpt":0.3022379049415592,"score_spread":0.2556988343917611,"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."}}