{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004373835,0.0008820389,0.001556132,0.0007277091,0.0008436462,0.001383337,0.001780877,0.00161379,0.003621093],"category_scores_gemma":[0.01901348,0.0004624947,0.0006753332,0.0007076818,0.002496869,0.003082048,0.001830249,0.002556794,0.0005249662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002771828,"about_ca_system_score_gemma":0.001941955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005226627,"about_ca_topic_score_gemma":0.00410579,"domain_scores_codex":[0.9977031,0.00132173,0.00008809721,0.0003148036,0.0003921004,0.0001800374],"domain_scores_gemma":[0.9918355,0.006048022,0.0007012808,0.0004022603,0.0006339406,0.0003790564],"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":[0.0001017534,0.00006983801,0.000965094,0.0001118957,0.00007037871,0.00007391539,0.0002090003,0.6531241,0.0005497026,0.3097782,0.001518839,0.03342729],"study_design_scores_gemma":[0.00002562698,0.00002122839,0.000101107,0.00001101286,0.000008810542,0.00001006193,0.00001426491,0.8093562,0.0001160313,0.1896356,0.0006908444,0.00000927055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01517582,0.0004105406,0.9783076,0.0007432711,0.00004742069,0.00005718478,0.00005464588,0.0001510586,0.005052465],"genre_scores_gemma":[0.8378596,0.0007760888,0.1558456,0.0002182797,0.0001347833,0.0003762175,0.0001567725,0.00006848799,0.004564219],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005226627,"threshold_uncertainty_score":0.02313131,"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."}}