The Value of Recall in Extensive-Form Games

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Berker, Ratip Emin, Tewolde, Emanuel, Anagnostides, Ioannis, Sandholm, Tuomas, Conitzer, Vincent
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913627716452352
author Berker, Ratip Emin
Tewolde, Emanuel
Anagnostides, Ioannis
Sandholm, Tuomas
Conitzer, Vincent
author_facet Berker, Ratip Emin
Tewolde, Emanuel
Anagnostides, Ioannis
Sandholm, Tuomas
Conitzer, Vincent
contents Imperfect-recall games, in which players may forget previously acquired information, have found many practical applications, ranging from game abstractions to team games and testing AI agents. In this paper, we quantify the utility gain by endowing a player with perfect recall, which we call the value of recall (VoR). While VoR can be unbounded in general, we parameterize it in terms of various game properties, namely the structure of chance nodes and the degree of absentmindedness (the number of successive times a player enters the same information set). Further, we identify several pathologies that arise with VoR, and show how to circumvent them. We also study the complexity of computing VoR, and how to optimally apportion partial recall. Finally, we connect VoR to other previously studied concepts in game theory, including the price of anarchy. We use that connection in conjunction with the celebrated smoothness framework to characterize VoR in a broad class of games.
format Preprint
id arxiv_https___arxiv_org_abs_2412_19659
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle The Value of Recall in Extensive-Form Games
Berker, Ratip Emin
Tewolde, Emanuel
Anagnostides, Ioannis
Sandholm, Tuomas
Conitzer, Vincent
Computer Science and Game Theory
91A05, 91A06, 91A10, 91A11, 91A18, 91A35, 91A68, 68T37, 68Q17, 68Q25
F.2; I.2; J.4
Imperfect-recall games, in which players may forget previously acquired information, have found many practical applications, ranging from game abstractions to team games and testing AI agents. In this paper, we quantify the utility gain by endowing a player with perfect recall, which we call the value of recall (VoR). While VoR can be unbounded in general, we parameterize it in terms of various game properties, namely the structure of chance nodes and the degree of absentmindedness (the number of successive times a player enters the same information set). Further, we identify several pathologies that arise with VoR, and show how to circumvent them. We also study the complexity of computing VoR, and how to optimally apportion partial recall. Finally, we connect VoR to other previously studied concepts in game theory, including the price of anarchy. We use that connection in conjunction with the celebrated smoothness framework to characterize VoR in a broad class of games.
title The Value of Recall in Extensive-Form Games
topic Computer Science and Game Theory
91A05, 91A06, 91A10, 91A11, 91A18, 91A35, 91A68, 68T37, 68Q17, 68Q25
F.2; I.2; J.4
url https://arxiv.org/abs/2412.19659