Suggesting new plot elements for an interactive story

Spyridon Giannatos, Mark J. Nelson, Yun-Gyung Cheong, Georgios N. Yannakakis (2011). Suggesting new plot elements for an interactive story. In Proceedings of the Workshop on Intelligent Narrative Technologies, pp. 25–30.


We present a system that uses evolutionary optimization to suggest new story-world events that, if added to an existing interactive story, would most improve the average interactive experience, according to author-supplied criteria. In doing so, we aim to apply some of the ideas from drama-managed storytelling, such as authorial aesthetic control, in an unguided setting more akin to emergent storytelling: rather than guiding or directing a player towards an experience in line with an author's aesthetic goals, the storyworld is augmented with new content in a way that will tend to align with an author's goals, even if the player is not guided. In this paper, we present an offline system, and demonstrate its robustness to a number of variations in authorial criteria and player-model assumptions. This is intended to lay the groundwork for a future system that would generate new content online allowing for interactive stories larger than those explicitly written by the author.

Back to publications.