Automated Construction of Bounded-loss Imperfect-recall Abstractions in Extensive-form Games

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F20%3A00345733" target="_blank" >RIV/68407700:21230/20:00345733 - isvavai.cz</a>

Result on the web

<a href="https://doi.org/10.1016/j.artint.2020.103248" target="_blank" >https://doi.org/10.1016/j.artint.2020.103248</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.artint.2020.103248" target="_blank" >10.1016/j.artint.2020.103248</a>

Result language

angličtina

Original language name

Automated Construction of Bounded-loss Imperfect-recall Abstractions in Extensive-form Games

Original language description

Extensive-form games (EFGs) model finite sequential interactions between players. The amount of memory required to represent these games is the main bottleneck of algorithms for computing optimal strategies and the size of these strategies is often impractical for real-world applications. A common approach to tackle the memory bottleneck is to use information abstraction that removes parts of information available to players thus reducing the number of decision points in the game. However, existing information-abstraction techniques are either specific for a particular domain, they do not provide any quality guarantees, or they are applicable to very small subclasses of EFGs. We present domain-independent abstraction methods for creating imperfect recall abstractions in extensive-form games that allow computing strategies that are (near) optimal in the original game. To this end, we introduce two novel algorithms, FPIRA and CFR+IRA, based on fictitious play and counterfactual regret minimization. These algorithms can start with an arbitrary domain specific, or the coarsest possible, abstraction of the original game. The algorithms iteratively detect the missing information they require for computing a strategy for the abstract game that is (near) optimal in the original game. This information is then included back into the abstract game. Moreover, our algorithms are able to exploit imperfect-recall abstractions that allow players to forget even history of their own actions. However, the algorithms require traversing the complete unabstracted game tree. We experimentally show that our algorithms can closely approximate Nash equilibrium of large games using abstraction with as little as 0.9% of information sets of the original game. Moreover, the results suggest that memory savings increase with the increasing size of the original games.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

Result was created during the realization of more than one project. More information in the Projects tab.

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2020

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Artificial Intelligence

ISSN

0004-3702

e-ISSN

1872-7921

Volume of the periodical

282

Issue of the periodical within the volume

May

Country of publishing house

GB - UNITED KINGDOM

Number of pages

36

Pages from-to

—

UT code for WoS article

000527317300004

EID of the result in the Scopus database

2-s2.0-85079664371