{"id":"W2924821341","doi":"","title":"Monte-Carlo Tree Search for Constrained MDPs","year":2018,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Monte Carlo tree search; Monte Carlo method; Computer science; Tree (set theory); Mathematical optimization; Mathematics; Statistics; Combinatorics","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":[],"consensus_categories":[],"category_scores_codex":[0.0003247423,0.00009583955,0.0001094806,0.00007010825,0.0001425845,0.0001488746,0.0008779611,0.00005155295,0.0001435103],"category_scores_gemma":[0.00008269095,0.00008035388,0.0000666234,0.0002178663,0.0002803178,0.0002926265,0.000165987,0.00005825798,0.0004362785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002341202,"about_ca_system_score_gemma":0.00008498111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009380269,"about_ca_topic_score_gemma":0.0001874786,"domain_scores_codex":[0.9989126,0.00002661243,0.000193442,0.0003275027,0.0001945478,0.0003452937],"domain_scores_gemma":[0.9989071,0.0002332424,0.00002664178,0.0004631454,0.0002747334,0.0000951731],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002145477,0.00007136325,0.0005930771,0.000008094,0.00002426708,0.000004909622,0.00263191,0.00005458275,0.00504147,0.478258,0.01496793,0.498323],"study_design_scores_gemma":[0.0001625207,0.0005996196,0.0003445807,0.00001268178,0.000004405473,0.00001156162,0.0005203551,0.6403702,0.3265703,0.0127849,0.01831433,0.0003045676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03322956,0.00001558455,0.9237377,0.002367235,0.0004461767,0.0002856975,0.000002343742,0.0002547838,0.03966093],"genre_scores_gemma":[0.8858841,0.000001477215,0.1097109,0.000429044,0.0002306579,0.00002000003,1.972252e-7,0.000006847554,0.00371674],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8526545,"threshold_uncertainty_score":0.5607623,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07943145295394001,"score_gpt":0.3377519798999285,"score_spread":0.2583205269459885,"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."}}