2021-07-21-giannou21a.md

title	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Survival of the strictest: Stable and unstable equilibria under regularized learning with partial information	In this paper, we examine the Nash equilibrium convergence properties of no-regret learning in general N -player games. For concreteness, we focus on the archetypal “follow the regularized leader” (FTRL) family of algorithms, and we consider the full spectrum of 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 equivalence extends existing continuous-time versions of the “folk theorem” of evolutionary game theory to a bona fide algorithmic learning setting, and it provides a clear refinement criterion for the prediction of the day-to-day behavior of no-regret learning in games.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	giannou21a	0	Survival of the strictest: Stable and unstable equilibria under regularized learning with partial information	2147	2148	2147-2148	2147	false	Giannou, Angeliki and Vlatakis-Gkaragkounis, Emmanouil Vasileios and Mertikopoulos, Panayotis	given family Angeliki Giannou given family Emmanouil Vasileios Vlatakis-Gkaragkounis given family Panayotis Mertikopoulos	2021-07-21		Proceedings of Thirty Fourth Conference on Learning Theory	134	inproceedings	date-parts 2021 7 21	http://proceedings.mlr.press/v134/giannou21a/giannou21a.pdf