{"id":"W4409632503","doi":"10.1016/b978-0-443-14081-5.00070-2","title":"Multi-Agent Reinforcement Learning Under General Information Structures","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Reinforcement learning; Reinforcement; Computer science; Psychology; Artificial intelligence; 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":[0.000346991,0.0006535826,0.0005414464,0.0002459506,0.0001452779,0.0008199622,0.0006830902,0.0007576321,0.006511965],"category_scores_gemma":[0.001233013,0.0002508469,0.0002888666,0.0004021807,0.0005734545,0.0009389525,0.0006875428,0.001196761,0.001116151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005741521,"about_ca_system_score_gemma":0.0003836914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001479539,"about_ca_topic_score_gemma":0.001334074,"domain_scores_codex":[0.9998628,0.00003731236,0.000007027144,0.00002617727,0.0000540543,0.00001259939],"domain_scores_gemma":[0.9996895,0.0002069037,0.00002355999,0.00002909606,0.00003650577,0.00001451443],"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":[0.00005673477,0.00005688077,0.0001849556,0.0001847939,0.00004292235,0.00008865847,0.00004591863,0.6449249,0.00345046,0.1058654,0.007774198,0.237324],"study_design_scores_gemma":[0.00001057743,0.00002348028,0.0001235713,0.00002468087,0.000006289965,0.00002940703,0.000006057094,0.9331057,0.000649386,0.05992178,0.006092855,0.000006223798],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01273928,0.002927662,0.9147192,0.0006417333,0.0002637715,0.00004007989,0.00007109492,0.0006056452,0.06799145],"genre_scores_gemma":[0.6363332,0.004759288,0.2326333,0.0002501062,0.0003186834,0.0002163203,0.0002851882,0.0002435054,0.1249604],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006511965,"threshold_uncertainty_score":0.02178466,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01837527086616969,"score_gpt":0.2495650173888868,"score_spread":0.2311897465227171,"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."}}