Research Repository

Evolution versus temporal difference learning for learning to play Ms. Pac-Man

Burrow, P and Lucas, SM (2009) Evolution versus temporal difference learning for learning to play Ms. Pac-Man. In: UNSPECIFIED, ? - ?.

Full text not available from this repository.


This paper investigates various factors that affect the ability of a system to learn to play Ms. Pac-Man. For this study Ms. Pac-Man provides a game of appropriate complexity, and has the advantage that in recent years there have been many other papers published on systems that learn to play this game. The results indicate that Temporal Difference Learning (TDL) performs most reliably with a tabular function approximator, and that the reward structure chosen can have a dramatic impact on performance. When using a multi-layer perceptron as a function approximator, evolution outperforms TDL by a significant margin. Overall, the best results were obtained by evolving multi-layer perceptrons. ©2009 IEEE.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Published proceedings: CIG2009 - 2009 IEEE Symposium on Computational Intelligence and Games
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Science and Health > Computer Science and Electronic Engineering, School of
Depositing User: Jim Jamieson
Date Deposited: 11 Oct 2012 13:33
Last Modified: 17 Aug 2017 18:07

Actions (login required)

View Item View Item