{"id":"W2149586740","doi":"10.1613/jair.4117","title":"Scalable and Efficient Bayes-Adaptive Reinforcement Learning Based on Monte-Carlo Tree Search","year":2013,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Gatsby Charitable Foundation; Royal Society","keywords":"Computer science; Monte Carlo tree search; Machine learning; Reinforcement learning; Tree (set theory); Scalability; Bayesian probability; Artificial intelligence; Benchmark (surveying); Monte Carlo method; Mathematical optimization; Mathematics; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005920767,0.0002316583,0.0003557622,0.001115288,0.0005681771,0.0009227186,0.00133085,0.0001230295,0.000210284],"category_scores_gemma":[0.001213522,0.0001894693,0.0001430999,0.001235439,0.0003529969,0.0005806473,0.0004591367,0.001896225,0.0003977752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000350236,"about_ca_system_score_gemma":0.0004203224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001783437,"about_ca_topic_score_gemma":0.000003472253,"domain_scores_codex":[0.9940898,0.0007208579,0.0009819152,0.0004229187,0.002825336,0.0009591772],"domain_scores_gemma":[0.9952742,0.001521527,0.0002982956,0.0005137672,0.001937616,0.0004546086],"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":[0.0000963148,0.00009252336,0.0001536136,0.00001775933,0.00002373833,0.00003500092,0.0008457404,0.9359654,0.001206642,0.005470461,0.0002098635,0.0558829],"study_design_scores_gemma":[0.00009566033,0.002882672,0.0002285956,0.0001811446,0.000004763602,0.00001497066,0.001209834,0.982104,0.01236411,0.0005515331,0.0001849819,0.0001777486],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04345198,0.00008065807,0.9511471,0.001706712,0.0002475839,0.0004875867,1.475204e-7,0.00003458473,0.002843666],"genre_scores_gemma":[0.987018,0.00006693841,0.01195211,0.00006725278,0.0001614995,0.00001319237,2.667204e-7,0.0000210606,0.0006996432],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.943566,"threshold_uncertainty_score":0.8897796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1097453708321637,"score_gpt":0.354419875162297,"score_spread":0.2446745043301333,"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."}}