Ευσταθή και ασταθή σημεία ισορροπίας σε εκμάθηση χωρίς regret και ενθόρυβα μοντέλα

Γιάννου, Αγγελική

dc.contributor.author	Γιάννου, Αγγελική
dc.date.accessioned	2022-02-01T15:33:37Z
dc.date.available	2022-02-01T15:33:37Z
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/54509
dc.identifier.uri	http://dx.doi.org/10.26240/heal.ntua.22207
dc.rights	Default License
dc.subject	Online Learning, Follow the Regularized Leader, Game Theory, Multi-agent Learning, Bandits	en
dc.subject	Θεωρία παιγνίων, Follow the Regularized Leader, Εκμάθηση σε περιβάλλοντα πολλών παικτών, Bandits.	el
dc.title	Ευσταθή και ασταθή σημεία ισορροπίας σε εκμάθηση χωρίς regret και ενθόρυβα μοντέλα	el
dc.contributor.department	Corelab	el
heal.type	bachelorThesis
heal.classification	Θεωρία παιγνίων	el
heal.language	el
heal.language	en
heal.access	free
heal.recordProvider	ntua	el
heal.publicationDate	2021-06-06
heal.abstract	In this diploma thesis, we examine the Nash equilibrium convergence properties of no-regret learning in general N-player games. Despite the importance and widespread applications of no-regret algorithms, their long-run behavior in multi-agent environments is still far from understood, and most of the literature has focused by necessity on certain, specific classes of games (typically zero-sum or congestion games). Instead of focusing on a fixed class of games, we instead take a structural approach and examine different classes of equilibria in generic games. For concreteness, we focus on the archetypal "follow the regularized leader" (FTRL) class of algorithms, and we consider the full spectrum of information uncertainty that the players may encounter – from noisy, oracle-based feedback, to bandit, payoff-based information. In this general context, we establish a comprehensive equivalence between the stability of a Nash equilibrium and its support: a Nash equilibrium is stable and attracting with arbitrarily high probability if and only if it is strict (i.e., each equilibrium strategy has a unique best response). This result extends existing continuous-time versions of the "folk theorem" of evolutionary game theory to a bona fide discrete-time learning setting, and provides an important link between the literature on multi-armed bandits and the equilibrium refinement literature.	en
heal.advisorName	Fotakis, Dimitris
heal.committeeMemberName	Pagourtzis, Aris
heal.committeeMemberName	Mertikopoulos, Panayotis
heal.committeeMemberName	Fotakis, Dimitris
heal.academicPublisher	Σχολή Ηλεκτρολόγων Μηχανικών και Μηχανικών Υπολογιστών	el
heal.academicPublisherID	ntua
heal.numberOfPages	63
heal.fullTextAvailability	false