{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004745243,0.0004845855,0.00037769,0.0003638072,0.0006252856,0.0003835787,0.0003715091,0.0003965187,0.0008058111],"category_scores_gemma":[0.0001702994,0.000534241,0.0001053878,0.000115875,0.00008759643,0.0009160081,0.0002403387,0.0008579915,0.0001325124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001255834,"about_ca_system_score_gemma":0.000122112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001334501,"about_ca_topic_score_gemma":0.000002521361,"domain_scores_codex":[0.997571,0.00009182664,0.0006475091,0.0005934309,0.000654572,0.0004416507],"domain_scores_gemma":[0.9980338,0.0001454081,0.0009095754,0.0003573959,0.0003405299,0.000213347],"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":[0.000004958766,0.0000038262,0.00009262943,0.00003892205,0.00005314526,0.000002432134,0.001634021,0.9017928,8.623766e-7,0.08558561,0.0002192403,0.01057152],"study_design_scores_gemma":[0.0002634528,0.0001691044,0.00001182984,0.00009166006,0.00005549957,0.00001010239,0.00005229205,0.7765715,0.000002312868,0.0002543843,0.2220662,0.0004517145],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[3.011519e-7,0.0007295642,0.7731844,0.00009499544,0.0002676383,0.0002676888,2.02991e-7,0.0003426714,0.2251126],"genre_scores_gemma":[0.01270158,0.005031708,0.1351108,0.0001447029,0.0003300501,0.00001930815,0.0004014485,0.0001228186,0.8461376],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.6380736,"threshold_uncertainty_score":0.9997109,"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."}}