{"id":"W2126848223","doi":"10.1007/978-3-642-15880-3_19","title":"Smarter Sampling in Model-Based Bayesian Reinforcement Learning","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"Office of Naval Research; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Reinforcement learning; Markov decision process; Approximate Bayesian computation; Bellman equation; Bayesian probability; Computation; Sample (material); Sampling (signal processing); Artificial intelligence; Posterior probability; Bayesian inference; Machine learning; Markov process; Algorithm; Mathematical optimization; Mathematics; Statistics","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":[0.005221676,0.0009284764,0.002537543,0.0006624556,0.0005498362,0.001370062,0.002728485,0.001969154,0.004748029],"category_scores_gemma":[0.02096405,0.001319064,0.0009586744,0.0009716811,0.002487487,0.003426012,0.002772881,0.003723845,0.00058555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001462171,"about_ca_system_score_gemma":0.001248234,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003592629,"about_ca_topic_score_gemma":0.003777498,"domain_scores_codex":[0.9973146,0.001544009,0.0001186977,0.0003368998,0.0005280192,0.000157802],"domain_scores_gemma":[0.9876912,0.0103512,0.000342114,0.0008532685,0.0004930655,0.0002690997],"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":[0.0002010812,0.0001003492,0.000418798,0.0001165711,0.00005785148,0.0000429284,0.00009519006,0.811312,0.0006364619,0.1324146,0.001533577,0.05307056],"study_design_scores_gemma":[0.00001542151,0.0000127906,0.00002507371,0.000004750031,0.000004394222,0.000005316263,0.000002131448,0.9549452,0.0001004085,0.04472211,0.0001585528,0.000003952769],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006517508,0.000269849,0.9912019,0.0001855747,0.00004336107,0.000026518,0.00002083362,0.0001675972,0.001566914],"genre_scores_gemma":[0.6128083,0.0005913003,0.3783869,0.000391063,0.0002128368,0.0003790697,0.0001919607,0.0002862432,0.006752436],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005221676,"threshold_uncertainty_score":0.02761519,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02126356525934251,"score_gpt":0.2552462471422459,"score_spread":0.2339826818829034,"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."}}