{"id":"W2461194651","doi":"","title":"A bayesian approach to multiagent reinforcement learning and coalition formation under uncertainty","year":2007,"lang":"en","type":"article","venue":"","topic":"Auction Theory and Applications","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Negotiation; Compromise; Artificial intelligence; Autonomous agent; Term (time); Multi-agent system; Bayesian probability","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":[0.002749816,0.00007112291,0.00008385105,0.0001572071,0.0003147087,0.0001090315,0.0001075322,0.00003888884,0.0002990949],"category_scores_gemma":[0.0002146198,0.00005251674,0.00002956432,0.0003947906,0.00003544737,0.0002603368,0.00005447241,0.00007201465,0.0001667521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004885314,"about_ca_system_score_gemma":0.000008903466,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002099707,"about_ca_topic_score_gemma":0.0000175158,"domain_scores_codex":[0.9987434,0.00006507473,0.0003825554,0.0002255674,0.000430464,0.0001529399],"domain_scores_gemma":[0.9992319,0.0002523491,0.0001019909,0.0001622012,0.0001153471,0.0001362529],"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":[0.00008047697,0.00007761067,0.0003076488,0.000005660726,0.00000926042,2.448427e-7,0.003012054,0.3958805,0.00152537,0.5186784,0.002819091,0.07760373],"study_design_scores_gemma":[0.0009158253,0.0001680775,0.004609289,0.00001318161,0.00001752144,0.00003479009,0.07140089,0.6346439,0.005317735,0.08731178,0.1951076,0.0004594212],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01802475,0.000004303129,0.926356,0.0005138952,0.00002993994,0.000264326,5.551607e-7,0.00004868978,0.05475752],"genre_scores_gemma":[0.9855465,0.000002211081,0.006655315,0.0005708805,0.00003399148,0.00002400889,0.00001250662,0.000003473211,0.007151171],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9675217,"threshold_uncertainty_score":0.3274879,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08626158008007274,"score_gpt":0.3835011666020686,"score_spread":0.2972395865219959,"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."}}