{"id":"W7124171798","doi":"10.65109/mlhm6027","title":"Bayesian Reinforcement Learning for Coalition Formation under Uncertainty","year":2004,"lang":"","type":"article","venue":"","topic":"Game Theory and Voting Systems","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Bayesian probability; Stability (learning theory); Bayesian inference; Core (optical fiber); Control (management)","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":[0.001954698,0.0002731329,0.0004891054,0.0002533848,0.0005342574,0.000227345,0.0001793716,0.0002360402,0.0006821436],"category_scores_gemma":[0.0001522017,0.0003320135,0.0002693241,0.0002140574,0.00005751925,0.0006773622,0.00004015056,0.0002138033,0.0005427288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000697438,"about_ca_system_score_gemma":0.00004899214,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003554818,"about_ca_topic_score_gemma":0.00005514873,"domain_scores_codex":[0.9974983,0.00004373577,0.001393886,0.0004456244,0.0000581247,0.0005603426],"domain_scores_gemma":[0.9985205,0.0001136692,0.0008628827,0.0002889493,0.00008480318,0.0001291841],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004609006,0.00003342962,0.000113652,0.0001641276,0.00003750383,1.621551e-7,0.0007752874,0.4904232,0.00001110063,0.5080726,0.00006372395,0.0002590855],"study_design_scores_gemma":[0.005232584,0.001033656,0.0002722534,0.0003287167,0.00004199833,0.00001315278,0.004760413,0.576538,0.0006388864,0.3753527,0.03487057,0.0009170982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02231298,0.0002894535,0.9478098,0.001156794,0.0009995938,0.001012752,0.00002331055,0.00007770062,0.02631768],"genre_scores_gemma":[0.9884295,0.000105946,0.0006326513,0.0003972851,0.0002886124,0.00009253519,0.0001813806,0.00003542279,0.009836634],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9661165,"threshold_uncertainty_score":0.9999132,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03765475217289617,"score_gpt":0.2417584993406987,"score_spread":0.2041037471678026,"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."}}