Cognitive gameplaying: playing games with cognitive computing

Authors
Ellis, Simon
ORCID
Loading...
Thumbnail Image
Other Contributors
Hendler, James A.
Bringsjord, Selmer
McGuinness, Deborah L.
Lynch, Michael F.
Issue Date
2016-08
Keywords
Computer science
Degree
PhD
Terms of Use
This electronic version is a licensed copy owned by Rensselaer Polytechnic Institute, Troy, NY. Copyright of original work retained by author.
Full Citation
Abstract
I present herein an alternative approach from ‘traditional’ game AI, derived from the concepts which underpin Watson’s technology, and demonstrate its usefulness in creating agents which can both play more complex, less game-theoretical, games and use a simple strategy to augment their move selection. This is the first tabletop (board, card, or role-playing) game AI to use the concepts and methods of cognitive computing in general and Watson in particular. The system will be demonstrated using the game Infinite City, published by Alderac Entertainment Group, a tile-based game in which players attempt to control sections of a ‘city’ represented by those tiles. Infinite City is highly mutable and can rapidly become combinatorially explosive, rendering it significantly less amenable to traditional game search methods.
Description
August 2016
School of Science
Department
Dept. of Computer Science
Publisher
Rensselaer Polytechnic Institute, Troy, NY
Relationships
Rensselaer Theses and Dissertations Online Collection
Access
Restricted to current Rensselaer faculty, staff and students. Access inquiries may be directed to the Rensselaer Libraries.