{"id":"W4389151102","doi":"10.1017/s0269888923000103","title":"Adaptive learning with artificial barriers yielding Nash equilibria in general games","year":2023,"lang":"en","type":"article","venue":"The Knowledge Engineering Review","topic":"Optimization and Search Problems","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Nash equilibrium; Computer science; Reinforcement learning; Learning automata; Game theory; Fictitious play; Convergence (economics); Saddle point; Mathematical economics; Normal-form game; Repeated game; Artificial intelligence; Mathematical optimization; Mathematics; Automaton; Economics","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":[],"consensus_categories":[],"category_scores_codex":[0.001010394,0.0001337021,0.0002145822,0.0001300703,0.00008308244,0.00007689655,0.0005045335,0.00002770068,0.00002606707],"category_scores_gemma":[0.0002720636,0.00009242191,0.00004621974,0.001589141,0.00002209452,0.0002009502,0.0002014798,0.0002899845,0.0001538335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004072264,"about_ca_system_score_gemma":0.00007943016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003013136,"about_ca_topic_score_gemma":0.000004479566,"domain_scores_codex":[0.9989544,0.0001145168,0.0002167369,0.0002292814,0.0001510749,0.0003339529],"domain_scores_gemma":[0.9993975,0.000159495,0.00003799748,0.0002651251,0.00004919851,0.00009069277],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000913101,0.00002868515,0.0002599481,0.001725276,0.00007156424,0.00004991327,0.005694879,0.7400066,0.001344936,0.08854524,0.002680759,0.159583],"study_design_scores_gemma":[0.00007843601,0.00003912023,0.0001188235,0.001583101,0.000004973996,0.000005268499,0.00002628442,0.9852122,0.00005498501,0.00007448638,0.01265309,0.0001492282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0268594,0.08573989,0.8685772,0.005036002,0.00121306,0.002284632,0.000002045764,0.002759715,0.007528019],"genre_scores_gemma":[0.8980535,0.04507547,0.0463306,0.000636272,0.000790301,0.000687448,0.00001897769,0.0002005622,0.008206827],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8711941,"threshold_uncertainty_score":0.3768856,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02775300846611881,"score_gpt":0.2696783488624332,"score_spread":0.2419253403963144,"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."}}