Evolving a Ms. PacMan Controller Using Grammatical Evolution
In this paper we propose an evolutionary approach capable of successfully combining rules to play the popular video game, Ms. Pac-Man. In particular we focus our attention on the benefits of using Grammatical Evolution to combine rules in the form of “if <condition> then perform <action>”. We defined a set of high-level functions that we think are necessary to successfully maneuver Ms. Pac-Man through a maze while trying to get the highest possible score. For comparison purposes, we used four Ms. Pac-Man agents, including a hand-coded agent, and tested them against three different ghosts teams. Our approach shows that the evolved controller achieved the highest score among all the other tested controllers, regardless of the ghost team used.
KeywordsDerivation Tree Grammatical Evolution Start Symbol Integer Array Neural Network Location
Unable to display preview. Download preview PDF.
- 1.Dempsey, I., O’Neill, M., Brabazon, A.: Foundations in Grammatical Evolution for Dynamic Environments. Springer, Heidelberg (2009), http://www.springer.com/engineering/book/978-3-642-00313-4 CrossRefGoogle Scholar
- 4.Lucas, S.: Ms Pac-Man Competition (September 2009), http://cswww.essex.ac.uk/staff/sml/pacman/PacManContest.html
- 5.Lucas, S.: Ms Pac-Man Competition - IEEE CIG 2009 (September 2009), http://cswww.essex.ac.uk/staff/sml/pacman/CIG2009Results.html
- 6.Lucas, S.: Ms Pac-Man versus Ghost-Team Competition. (September 2009), http://csee.essex.ac.uk/staff/sml/pacman/kit/AgentVersusGhosts.html
- 7.Lucas, S.: Evolving a neural network location evaluator to play ms. pac-man. In: IEEE Symposium on Computational Intelligence and Games, pp. 203–210 (2005)Google Scholar
- 9.O’Neill, M., Hemberg, E., Gilligan, C., Bartley, E., McDermott, J., Brabazon, A.: GEVA - grammatical evolution in java (v 1.0). Tech. rep., UCD School of Computer Science (2008)Google Scholar