"Using Cultural Coevolution for Learning in General Game Playing" by Shiven Sharma

Date of Award

2009

Publication Type

Master Thesis

Degree Name

M.Sc.

Department

Computer Science

Keywords

Applied sciences

Supervisor

Ziad Kobti

Supervisor

Scott D. Goodwin

Rights

info:eu-repo/semantics/openAccess

Abstract

Traditionally, the construction of game playing agents relies on using pre-programmed heuristics and architectures tailored for a specific game. General Game Playing (GGP) provides a challenging alternative to this approach, with the aim being to construct players that are able to play any game, given just the rules. This thesis describes the construction of a General Game Player that is able to learn and build knowledge about the game in a multi-agent setup using cultural coevolution and reinforcement learning. We also describe how this knowledge can be used to complement UCT search, a Monte-Carlo tree search that has already been used successfully in GGP. Experiments are conducted to test the effectiveness of the knowledge by playing several games between our player and a player using random moves, and also a player using standard UCT search. The results show a marked improvement in performance when using the knowledge.

Share

COinS