{"id":"W4394775968","doi":"10.48550/arxiv.2404.06516","title":"Convergence to Nash Equilibrium and No-regret Guarantee in (Markov) Potential Games","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Regret; Nash equilibrium; Mathematical optimization; Best response; Correlated equilibrium; Computer science; Sublinear function; Epsilon-equilibrium; Convergence (economics); Markov chain; Stackelberg competition; Markov decision process; Flexibility (engineering); Mathematical economics; Mathematics; Markov process; Game theory; Equilibrium selection; Repeated game; Economics; Statistics; Discrete mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004091364,0.001548112,0.00198685,0.0007515191,0.001014588,0.001885748,0.00185451,0.001783616,0.003094504],"category_scores_gemma":[0.02618642,0.0006907837,0.000915043,0.0008254758,0.002085108,0.003459058,0.00223915,0.002605847,0.0006575236],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001908418,"about_ca_system_score_gemma":0.002537167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00348934,"about_ca_topic_score_gemma":0.003671398,"domain_scores_codex":[0.9968401,0.001694002,0.0001084845,0.0004578195,0.0004332161,0.0004662952],"domain_scores_gemma":[0.9843785,0.01307222,0.0007348145,0.0006459665,0.0006479967,0.0005205201],"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":[0.000286182,0.0001221459,0.0009339384,0.0001749688,0.00006576064,0.0001147241,0.0001288925,0.8252498,0.001154565,0.1473657,0.001851618,0.02255172],"study_design_scores_gemma":[0.00002222234,0.00002974481,0.00006541277,0.00001152915,0.000005555209,0.00002194596,0.00001512175,0.9370852,0.0003165049,0.06220012,0.0002197171,0.000006886249],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05498999,0.0004805328,0.9366806,0.0008017696,0.00005133417,0.0001047048,0.0001223636,0.0003461709,0.006422521],"genre_scores_gemma":[0.8627475,0.0005056373,0.1314279,0.0003518759,0.00006527232,0.0003158159,0.000172745,0.0001891018,0.0042242],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004091364,"threshold_uncertainty_score":0.0216375,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1261491593914093,"score_gpt":0.2994446837724387,"score_spread":0.1732955243810294,"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."}}