Player-customized puzzle instance generation for Massively Multiplayer Online Games

Massively Multiplayer Online Games (MMOGs) have emerged as a new type of interactive application simultaneously played by millions around the world. Besides social interaction, players are entertained by content such as virtual world objects and logical challenges. Thus, developing content of good quality and in sufficient quantity is key for a successful MMOG. Currently, the content is generated exclusively by teams of human content designers, but the growth of the player population, the lack of scalability of the production pipeline, and the increase in the price ratio between human work and computation make this situation undesirable for the future. The paper investigates the problem of fully automated content generation for MMOGs, such that customized content that matches taste and previous game experience is available for each player. We take as a motivating example of content instances of puzzle games, that is, games in which the player is entertained by solving a logical challenge; for example, different players may each spend hours to solve different instances of chess puzzles to open the gates to the Labyrinth.