{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00159624,0.0007641944,0.0006829386,0.00170285,0.0003719922,0.0008467562,0.003978687,0.0006171573,0.00004512102],"category_scores_gemma":[0.0002055132,0.0007677557,0.0001779081,0.0007412648,0.0005763785,0.0007211351,0.00137564,0.003283526,0.00005289635],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005631926,"about_ca_system_score_gemma":0.001005433,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002459677,"about_ca_topic_score_gemma":0.00007887761,"domain_scores_codex":[0.9944823,0.0000467728,0.0009898845,0.001775143,0.001522866,0.001183013],"domain_scores_gemma":[0.9967131,0.0005229942,0.0005077651,0.00178085,0.0002283624,0.0002469418],"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":[0.000004929658,0.00000959629,0.0001578923,0.00003588917,0.000004531353,0.00003427021,0.0004920387,0.938483,0.0001907556,0.004300442,0.000001403026,0.05628528],"study_design_scores_gemma":[0.0004266744,0.0001690756,0.00004195992,0.0004742277,0.000005699595,0.0000120804,1.362108e-7,0.9824457,0.0006365157,0.01424631,0.0007294797,0.0008121651],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00003429864,0.00004753754,0.9923826,0.0004938528,0.001316495,0.0005160804,4.398007e-7,0.0002359002,0.00497281],"genre_scores_gemma":[0.3473456,0.00001177247,0.650213,0.001371191,0.0002167242,0.00001472817,0.00001049696,0.00005860313,0.0007578643],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3473113,"threshold_uncertainty_score":0.9994773,"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."}}