ERA

Download the full-sized PDF of Regret Minimization in Games with Incomplete InformationDownload the full-sized PDF

Analytics

Share

Permanent link (DOI): https://doi.org/10.7939/R3Q23R282

Download

Export to: EndNote  |  Zotero  |  Mendeley

Communities

This file is in the following communities:

Computing Science, Department of

Collections

This file is in the following collections:

Technical Reports (Computing Science)

Regret Minimization in Games with Incomplete Information Open Access

Descriptions

Author or creator
Zinkevich, Martin
Johanson, Michael
Bowling, Michael
Piccione, Carmelo
Additional contributors
Subject/Keyword
Computer Games
Regret minimization
Extensive games
Poker
Game theory
Type of item
Computing Science Technical Report
Computing science technical report ID
TR07-14
Language
English
Place
Time
Description
Technical report TR07-14. Extensive games are a powerful model of multiagent decision-making scenarios with incomplete information. Finding a Nash equilibrium for very large instances of these games has received a great deal of recent attention. In this paper, we describe a new technique for solving large games based on regret minimization. In particular, we introduce the notion of counterfactual regret, which exploits the degree of incomplete information in an extensive game. We show how minimizing counterfactual regret minimizes overall regret, and therefore in self-play can be used to compute a Nash equilibrium. We demonstrate this technique in the domain of poker, showing we can solve abstractions of limit Texas Hold'em with as many as 10^12 states, two orders of magnitude larger than previous methods.
Date created
2007
DOI
doi:10.7939/R3Q23R282
License information
Creative Commons Attribution 3.0 Unported
Rights

Citation for previous publication

Source
Link to related item

File Details

Date Uploaded
Date Modified
2014-05-01T04:07:58.292+00:00
Audit Status
Audits have not yet been run on this file.
Characterization
File format: pdf (Portable Document Format)
Mime type: application/pdf
File size: 249123
Last modified: 2015:10:12 17:06:11-06:00
Filename: TR07-14.pdf
Original checksum: 1f9b9e01468c55909e44679748ce0631
Well formed: false
Valid: false
Status message: Lexical error offset=245147
Page count: 14
Activity of users you follow
User Activity Date