{"id":"W1862757251","doi":"10.1007/978-3-642-27645-3_11","title":"Bayesian Reinforcement Learning","year":2012,"lang":"en","type":"book-chapter","venue":"Adaptation, learning, and optimization","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Bayesian probability; Artificial intelligence; Computer science; Machine learning; Posterior probability; Prior probability; Domain (mathematical analysis); Bayesian inference; Function (biology); Bellman equation; Mathematics; Mathematical optimization","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":[0.0006014961,0.0009676237,0.0007593684,0.0005269164,0.0003618206,0.001478524,0.001213073,0.001158472,0.01932428],"category_scores_gemma":[0.002047532,0.0004153423,0.0003997116,0.0006791801,0.001028034,0.00134839,0.0009619637,0.001926221,0.006463266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001059602,"about_ca_system_score_gemma":0.0008514033,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00172049,"about_ca_topic_score_gemma":0.002574112,"domain_scores_codex":[0.9995928,0.00009560728,0.00001511948,0.00008715635,0.0001820344,0.00002718368],"domain_scores_gemma":[0.9996562,0.0001684964,0.00002213659,0.00005379026,0.00007422722,0.00002511672],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004147101,0.00008202713,0.0001782472,0.0002415202,0.00004260218,0.00004148165,0.00006927221,0.04496744,0.001293524,0.4711124,0.05185455,0.4300755],"study_design_scores_gemma":[0.0000226494,0.00004149238,0.0003365673,0.000179806,0.00002396833,0.000144733,0.0000257162,0.1405322,0.001564326,0.6593753,0.1977106,0.00004265243],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.001963926,0.01328689,0.7720085,0.001902716,0.0006979015,0.00006993876,0.0002254593,0.0009358386,0.2089088],"genre_scores_gemma":[0.2597352,0.0276071,0.3510259,0.001440576,0.001311622,0.0004656735,0.001114795,0.0006878257,0.3566113],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.01932428,"threshold_uncertainty_score":0.06464612,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0155417566294811,"score_gpt":0.2220733637607066,"score_spread":0.2065316071312255,"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."}}