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.
|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|
Copyright in each Dissertation and Thesis is retained by the author. All Rights Reserved
dissertation or thesis. The supplemental files are provided "AS IS" without warranty. ProQuest is not responsible for the
content, format or impact on the supplemental file(s) on our system. in some cases, the file type may be unknown or
may be a .exe file. We recommend caution as you open such files.
supplemental files is subject to the ProQuest Terms and Conditions of use.