2024-04-18-bernasconi24a.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
Learning Extensive-Form Perfect Equilibria in Two-Player Zero-Sum Sequential Games	Designing efficient algorithms for computing refinements of the Nash equilibrium (NE) in two-player zero-sum sequential games is of paramount importance, since the NE may prescribe sub-optimal actions off the equilibrium path. The extensive-form perfect equilibrium (EFPE) amends such a weakness by accounting for the possibility that players may make mistakes. This is crucial in the real world, which involves humans with bounded rationality, and it is also key in boosting superhuman agents for games like Poker. Nevertheless, there are only few algorithms for computing NE refinements, which either lack convergence guarantees to exact equilibria or do not scale to large games. We provide the first efficient iterative algorithm that provably converges to an EFPE in two-player zero-sum sequential games. Our algorithm works by tracking a sequence of equilibria of regularized-perturbed games, by using a procedure that is specifically tailored to converge last iterate to such equilibria. The procedure can be implemented efficiently by visiting the game tree, making our method computationally appealing. We also empirically evaluate our algorithm, showing that its strategies are much more robust to players’ mistakes than those of state-of-the-art algorithms.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	bernasconi24a	0	Learning Extensive-Form Perfect Equilibria in Two-Player Zero-Sum Sequential Games	2152	2160	2152-2160	2152	false	Bernasconi, Martino and Marchesi, Alberto and Trov\`{o}, Francesco	given family Martino Bernasconi given family Alberto Marchesi given family Francesco Trovò	2024-04-18		Proceedings of The 27th International Conference on Artificial Intelligence and Statistics	238	inproceedings	date-parts 2024 4 18	https://proceedings.mlr.press/v238/bernasconi24a/bernasconi24a.pdf