Cheong, Yun-Gyung
Organizers
Tomuro, Noriko (DePaul University) | Boyer, Kristy (North Carolina State University) | Cheong, Yun-Gyung (IT University of Copenhagen)
Objective
Tomuro, Noriko (DePaul University) | Boyer, Kristy (North Carolina State University) | Cheong, Yun-Gyung (IT University of Copenhagen)
Generating Narrative Action Schemas for Suspense
Giannatos, Spyridon (IT University of Copenhagen) | Cheong, Yun-Gyung (IT University of Copenhagen) | Nelson, Mark J. (IT University of Copenhagen) | Yannakakis, Georgios N. (IT University of Copenhagen)
A bottleneck in interactive storytelling is the authorial burden of writing narrative units, and connecting them to the interactive narrative structure. To address this problem, we present a hybrid approach that combines AI planning and evolutionary optimization in order to generated new plan operators representing possible story actions, within the framework of a planning-based interactive narrative system. We focus our work on inventing plan operators that are useful for contributing to suspenseful interactive stories, using suspense metrics that have been proposed in the literature. We devise an encoding scheme for converting a plan operator into a genetic-algorithm chromosome and vice versa, respecting constraints that are needed for an operator to be well-formed. We discuss the performance of the system, and several examples from preliminary experiments carried out to evaluate the evolved operators.
Suggesting New Plot Elements for an Interactive Story
Giannatos, Spyridon (IT University of Copenhagen) | Nelson, Mark J. (IT University of Copenhagen) | Cheong, Yun-Gyung (IT University of Copenhagen) | Yannakakis, Georgios N. (IT University of Copenhagen)
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.