{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001441179,0.0004163907,0.0006436483,0.0003245703,0.0002022595,0.0007237608,0.0007469197,0.0002225871,0.0007514166],"category_scores_gemma":[0.0001741805,0.0002827967,0.0001725118,0.0001504618,0.00008073603,0.0003666324,0.0001404398,0.000423534,0.008293876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001402159,"about_ca_system_score_gemma":0.0001555408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005961753,"about_ca_topic_score_gemma":0.00001625798,"domain_scores_codex":[0.996315,0.00007916583,0.001282648,0.0005508566,0.001438558,0.0003337578],"domain_scores_gemma":[0.9974384,0.0002754427,0.0006664697,0.0008508592,0.0005127135,0.0002560722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001295917,0.000003503139,0.00002650802,0.00007493336,0.0001941791,0.00000933992,0.001077095,0.1359099,0.0005963997,0.8556839,0.004165856,0.002128804],"study_design_scores_gemma":[0.0007323281,0.0001869737,0.00004259018,0.0002442536,0.0001064565,0.00002626324,0.0003704635,0.06447218,0.00001611102,0.008581419,0.9247524,0.0004685619],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002881863,0.001189577,0.5249808,0.0007303562,0.004051305,0.006672379,0.0003387295,0.0004926446,0.4586624],"genre_scores_gemma":[0.5289208,0.000005419758,0.0001373996,0.0001880628,0.0002465719,0.0001580504,0.00003664361,0.00002613588,0.470281],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.9205865,"threshold_uncertainty_score":0.9999624,"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."}}