{"id":"W2143362857","doi":"10.1109/aamas.2004.74","title":"Bayesian Reinforcement Learning for Coalition Formation under Uncertainty","year":2004,"lang":"en","type":"article","venue":"","topic":"Game Theory and Voting Systems","field":"Economics, Econometrics and Finance","cited_by":118,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Certainty; Core (optical fiber); Bayesian probability; Computer science; Stability (learning theory); Artificial intelligence; Bayesian inference; Machine learning; Mathematics","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":[0.0006282176,0.00007175288,0.0001389522,0.00007877993,0.0001374643,0.00004530471,0.00005883846,0.00005163856,0.0001635605],"category_scores_gemma":[0.00005020169,0.00007756978,0.00006590999,0.0000648764,0.00001245718,0.0002271837,0.0000096147,0.00005319291,0.0002216173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001516013,"about_ca_system_score_gemma":0.000007193575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001577567,"about_ca_topic_score_gemma":0.00002088078,"domain_scores_codex":[0.9992966,0.000008239664,0.0003745954,0.0001359632,0.00001776662,0.0001668523],"domain_scores_gemma":[0.9996282,0.00002965303,0.0001892018,0.00009883432,0.00002049929,0.00003365477],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000008942297,0.000007452985,0.0001196725,0.00002430046,0.000006852872,4.438869e-8,0.0002326132,0.3209686,0.00001406816,0.6784881,0.00005517535,0.00007414459],"study_design_scores_gemma":[0.002494923,0.0003176873,0.0004527621,0.00006238759,0.000006795111,0.000006392702,0.00153385,0.1794717,0.0007995593,0.7805085,0.03395633,0.0003890829],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02446596,0.00003461396,0.9429088,0.00046135,0.0001742586,0.0002652664,0.000004044264,0.00006585699,0.03161991],"genre_scores_gemma":[0.9957705,0.000005735254,0.0005720384,0.0002318034,0.00007240978,0.00003972283,0.000061818,0.000009414375,0.003236621],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9713045,"threshold_uncertainty_score":0.3163204,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03862522706976329,"score_gpt":0.2371829084291786,"score_spread":0.1985576813594153,"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."}}