{"id":"W4399828050","doi":"10.1007/978-3-031-54071-4_23","title":"Multi-Agent Reinforcement Learning with General Information Structures: Convergence to Equilibria","year":2024,"lang":"en","type":"book-chapter","venue":"Systems & control","topic":"Game Theory and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Reinforcement learning; Convergence (economics); Computer science; Reinforcement; Artificial intelligence; Psychology; Economics; Social psychology","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":[0.002163348,0.0009479505,0.001319664,0.0006746173,0.0006392642,0.001669468,0.001831788,0.001848928,0.004473527],"category_scores_gemma":[0.01500859,0.0006238156,0.0009224944,0.0007352049,0.001841877,0.002581928,0.002327553,0.002831143,0.0006425306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001622159,"about_ca_system_score_gemma":0.001090819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00252388,"about_ca_topic_score_gemma":0.001604991,"domain_scores_codex":[0.9992625,0.0003468172,0.00002598669,0.0001185661,0.0001555118,0.00009065439],"domain_scores_gemma":[0.9939994,0.004851911,0.0002770776,0.0002884803,0.000400772,0.0001824224],"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":[0.0001369778,0.0001121642,0.0005213387,0.0002387377,0.00009493205,0.0001065631,0.0002069802,0.488606,0.001695484,0.4577065,0.004339166,0.04623499],"study_design_scores_gemma":[0.00001962876,0.00002504333,0.00009095242,0.00002036416,0.000007249903,0.0000254393,0.0000203755,0.8347133,0.0002407542,0.1642009,0.00063004,0.000006043851],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0597769,0.001453846,0.8904326,0.001088426,0.000121235,0.0001230502,0.00008748152,0.0003060957,0.04661045],"genre_scores_gemma":[0.8382798,0.00138683,0.1382849,0.0002699003,0.0001190463,0.0003789579,0.0001463014,0.000213526,0.0209207],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004473527,"threshold_uncertainty_score":0.01496547,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04695434048677424,"score_gpt":0.3173914437629703,"score_spread":0.2704371032761961,"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."}}