Year: 2005
Type: article
Abstract: This paper constitutes a sequel to our previous work \nfocused on investigating cooperative behaviors, adaptive learning \nand on-line interaction towards the generation of entertainment \nin computer games. A human-verified metric of interest (i.e. \n \nplayer entertainment) of predator/prey games and a neuro- \nevolution on-line learning (i.e. during play) approach are used to \n \nserve this purpose. Experiments presented here demonstrate the \ngenerality of the proposed approach, in its ability to overcome \nthe difficulties of learning in real-time and generate interesting \npredator/prey games, over game type, complexity, topology, initial \nopponent behavior and player type.
Authors: Georgios N. Yannakakis, John Hallam
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2802359771
