POGGI: generating puzzle instances for online games on grid infrastructures

摘要

The developers of Massively multiplayer online games (MMOGs) rely on attractive content such as logical challenges (puzzles) to entertain and generate revenue from millions of concurrent players. While a large part of the content is currently generated by hand, the exponentially increasing number of players and their new demand for player-customized content have made manual content generation undesirable. Thus, in this work we investigate the problem of automated, player-customized game content generation at MMOG scale; to make our investigation tractable, we focus on puzzle game content generation. In this context, we design POGGI, an architecture for generating player-customized game content using on-demand, grid resources. POGGI focuses on the large-scale generation of puzzle instances that match well the solving ability of the players, and that lead to fresh playing experience. Using our reference implementation of POGGI, we show through experiments in a real resource pool of over 1600 nodes that POGGI can generate commercial-quality content at MMOG scale.