Dissertation/Thesis Abstract

Goal-Based Agent Design: Decision Making in General Game Playing
by Sheng, Xinxin, Ph.D., North Carolina State University, 2011, 180; 3497189
Abstract (Summary)

General Game Playing's primary research thrust is building automated intelligent computer agents that accept declarative descriptions of arbitrary games at run-time and are capable of using such descriptions to play effectively without human intervention. The research in general game playing approximates human cognitive processes, sophisticated planning, and problem solving with an instant reward system represented in games. General game playing has well-recognized research areas with diverse topics including knowledge representation, search, strategic planning, and machine learning. It attacks the general intelligence problem that Artificial Intelligence researchers have made little progress on for the last several decades. We have designed and implemented an automated goal-based general game playing agent that is capable of playing most games written in the Game Description Language and has shown excellent results for general-purpose learning in the general game playing environment. Our contributions include: the general game playing agent designed to play a wide variety of games, the knowledge reasoning performance improvement algorithm, the run-time feature identification algorithm, the contextual decision-making algorithm, and the GDL extension to enrich the game domain.

Indexing (document details)
Advisor: Thuente, David
School: North Carolina State University
School Location: United States -- North Carolina
Source: DAI-B 73/05, Dissertation Abstracts International
Subjects: Computer Engineering, Computer science
Keywords: Agent design, Decision making, Game playing, Learning
Publication Number: 3497189
ISBN: 978-1-267-17675-2
Copyright © 2021 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy