{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004902266,0.0008463927,0.001576145,0.0008181768,0.0008090983,0.001395742,0.001761956,0.001433091,0.003479143],"category_scores_gemma":[0.01964707,0.000490303,0.0007217898,0.0007045299,0.002420958,0.003082691,0.0018139,0.002523286,0.0004717283],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002801649,"about_ca_system_score_gemma":0.002074972,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005121906,"about_ca_topic_score_gemma":0.004095755,"domain_scores_codex":[0.9974803,0.001405669,0.000102207,0.000367009,0.0004395594,0.0002051652],"domain_scores_gemma":[0.9910129,0.006584186,0.0008430213,0.000461235,0.0006642215,0.0004344668],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009711585,0.00007413946,0.0009792735,0.0001022344,0.00007962428,0.00007123126,0.0002070938,0.6886402,0.0005461745,0.2760406,0.001248561,0.03191382],"study_design_scores_gemma":[0.00002568905,0.00002120848,0.0001029026,0.00001035207,0.000008190817,0.000009855618,0.00001575327,0.8148221,0.0001313281,0.1841876,0.0006560176,0.000008913375],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01727306,0.0003612365,0.9768313,0.000694279,0.00004444884,0.00005695708,0.00004932798,0.0001399983,0.004549303],"genre_scores_gemma":[0.8425213,0.0006390371,0.151713,0.0002028865,0.0001159237,0.0003458463,0.0001525667,0.00006788027,0.004241573],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005121906,"threshold_uncertainty_score":0.02592599,"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."}}