Learning and Using Hand Abstraction Values for Parameterized Poker Squares


Student Authors:

Colin M. Messinger '17, Gettysburg College

Zuozhi Yang '17, Gettysburg College

Document Type

Conference Material

Publication Date


Department 1

Computer Science


We describe the experimental development of an AI player that adapts to different point systems for Parameterized Poker Squares. After introducing the game and research competition challenge, we describe our static board evaluation utilizing learned evaluations of abstract partial Poker hands. Next, we evaluate various time management strategies and search algorithms. Finally, we show experimentally which of our design decisions most significantly accounted for observed performance.


Presented during the 30th AAAI Conference on Artificial Intelligence on February 12th, 2016.

Required Publisher's Statement

Original version available from publisher at http://www.aaai.org/Press/Proceedings/aaai16.php