This chapter investigates alternative notions of both convergence and equilibrium. By studying the asymptotic behaviour of certain classes of learning dynamics, we are led to more inclusive definitions of what constitutes equilibrium behaviour in a game. The chapter begins by introducing a general concept of equilibrium that includes both Nash equilibrium and correlated equilibrium as special cases. It then shows that this notion of equilibrium is precisely what regret matching converges to.
Oxford Scholarship Online requires a subscription or purchase to access the full text of books within the service. Public users can however freely search the site and view the abstracts and keywords for each book and chapter.
If you think you should have access to this title, please contact your librarian.