{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003207047,0.0006528313,0.0005315722,0.0005131701,0.000360682,0.0005468657,0.001359247,0.0004424541,0.0001420896],"category_scores_gemma":[0.00004948406,0.0006355854,0.0002938756,0.00004503359,0.00009166418,0.0004908929,0.00107361,0.001130296,0.0003469478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003938066,"about_ca_system_score_gemma":0.0003470391,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001930661,"about_ca_topic_score_gemma":0.000002261726,"domain_scores_codex":[0.9970117,0.00005256691,0.0009995865,0.0005100654,0.0008937562,0.0005322916],"domain_scores_gemma":[0.9976746,0.00006843439,0.0007442325,0.001093136,0.0002578348,0.0001617199],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003537808,0.000001253031,0.000002410791,0.00009100566,0.000119315,0.000004955763,0.0003392975,0.4267704,0.000006414321,0.1308041,0.0003293587,0.4415279],"study_design_scores_gemma":[0.0004331405,0.00008203529,0.00002538974,0.0002237776,0.00005449413,0.000007107665,0.000008180538,0.1867044,0.00003684395,0.001727714,0.810123,0.0005739665],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00000103255,0.00009532148,0.4215192,0.00005608968,0.000802586,0.0004465767,0.000001280723,0.0002298667,0.5768481],"genre_scores_gemma":[0.0005813891,0.00008916661,0.03509736,0.001402654,0.0001569247,0.00002900701,0.0001062869,0.00003649847,0.9625007],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.8097936,"threshold_uncertainty_score":0.9996095,"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."}}