Back to Results
First PageMeta Content
Structure / Mathematics / Science / Game theory / Determinacy / Extensive-form game


No-Regret Learning in Extensive-Form Games with Imperfect Recall Marc Lanctot1 Richard Gibson1 Neil Burch1 Martin Zinkevich2
Add to Reading List

Document Date: 2012-06-07 13:19:52

Open Document

File Size: 342,90 KB

Share Result on Facebook

City

Edmonton / Sunnyvale / Edinburgh / /

Company

Neural Information Processing Systems / MIT Press / Multiagent Systems / Morgan Kaufmann Publishers Inc. / Computer Poker Research Group / Canada T6G 2E8 2 Yahoo! Inc. / /

Country

United States / United Kingdom / Scotland / /

Event

Product Recall / Product Issues / /

Facility

University of Alberta / /

IndustryTerm

e-prints / tive no-regret learning algorithm / no-regret algorithm / final utilities / no-regret learning algorithm / /

Organization

MIT / University of Alberta / /

Person

Alberta Innovates / Ai / /

Position

special player / RT / player / removing player / author / much player / same player / losing player / utility player / enforcing player / /

Product

refinement / version of PTTT / game / extensive games / abstractions of Texas Hold’em poker / Imperfect / An extensive game / games / settings / zero-sum imperfect / /

ProvinceOrState

Kansas / /

PublishedMedium

Games and Economic Behavior / Machine Learning / Theory of Computing / /

SportsGame

Bowling / /

Technology

no-regret algorithm / worth four chips / worth two chips / Machine Learning / no-regret learning algorithm / CFR algorithm / tive no-regret learning algorithm / /

SocialTag