Group items tagged

Abstract: "Procedural generation of games has become an active re- search eld. We present a system that automatically gen- erates an interactive ction (IF) by learning from crowd- sourced corpora of example stories. We ask crowd workers from Amazon Mechanical Turk to write short stories about a given situation with simple language, from which a plot graph is learned, containing plot events, temporal prece- dence and mutual exclusion relations between the events. The plot graph describes an IF where players and non-player characters choose from executable events as determined by the plot graph. We demonstrate an IF learned from the domain of bank robbery"

Abstract: "As computer games are an increasingly large industry, it is becoming increasingly important for people working in the eld to understand what elements of the game engage the player so as to improve the design of the game. By studying common techniques used in modern games, this paper looks to highlight how the techniques work and thereby provide developers and designers with more information to improve the use of these techniques in future games. The paper also re ects upon the applicability of these techniques outside of games specifically."