Playable Experiences at AIIDE 2018

Experience Management uses AI technologies to improve people's experiences within an interactive application by changing the environment while the experience is underway. Game-related research in this field has a trend where each experience manager is built in a way that is tightly integrated with the environment that it can change. One consequence of this integration is that it becomes difficult to compare one manager to another in a single environment, or a single manager to itself across multiple environments. With this paper, we propose a solution for decoupling experience managers from the environments that they can change, through the use of an intermediate software platform. We describe the structure of the platform, a protocol that facilitates communication between a manager and an environment, and how normal communication happens. Moreover, we introduce the Camelot Wrapper, software built to extend the interactive visualization engine Camelot and connect it to our platform.

Section: Camelot Wrappermentioning

confidence: 99%

“…One work that can be used to build an environment for our platform is Camelot (Samuel et al 2018;Shirvani and Ware 2020), a visualization engine developed by the Narrative Intelligence Lab at the University of Kentucky. Camelot provides a sandbox to visualize and test different narrative systems.…”

Section: Introductionmentioning

confidence: 99%

EM-Glue: A Platform for Decoupling Experience Managers and Environments

Mori

Thue

Schiffel

2022

“…Our belief model supports infinite layers of nested beliefs, where each layer represents what character x believes about what character y believes. We used a very simplified version of the model in a 3D interactive virtual environment (Samuel et al 2018;Ware et al 2019). However, my focus is not character beliefs, but rather modeling individual and distinct behavior.…”

Section: My Previous Workmentioning

confidence: 99%

Towards More Believable Characters Using Personality and Emotion

Shirvani

2019

Interactive virtual worlds provide an immersive and effective environment for training, education, and entertainment purposes. So far, there have been considerable advances in 3D and AI design to enhance virtual environments. Virtual characters are one of the crucial aspects of interactive narratives. The interaction of rich virtual characters can produce interesting narrative and as a result, enhance the experience of virtual environments. As one of those characters, the user would feel immersed and engaged when interacting with compelling characters. There are many characteristics that improve believable behavior generation, including beliefs, goals, desires, affect, and personality. My goal is to propose an affective model of personality for multi-agent narrative planning systems that is domain independent and thus minimizes authorial burden. I aim to combine existing models into a unified framework. Although the framework may oversimply those models, it would not overlook their key ingredients.

“…Planning algorithms have been adapted to ensure that agents only act in ways that they expect to contribute to achieving their goals (Riedl and Young 2010;Teutenberg and Porteous 2015;Shirvani, Ware, and Farrell 2017;Samuel et al 2018;Ware et al 2019). They rarely distinguish between different plans to achieve the same goal, even when they have different effects on other characters (Bahamón, Barot, and Young 2015).…”

Section: Introductionmentioning

confidence: 99%

A Plan-Based Personality Model for Story Characters

Shirvani

Ware

2019

Believable virtual characters enhance the experience of interactive virtual worlds. BDI-based state-space narrative planners make their characters more compelling by granting them specific goals to pursue and different (possibly wrong) beliefs about the state of the world. However, such systems do not account for character individuality. We extend work on narrative planning by proposing a personality model based on the Big Five. This paper discusses how each factor of the Big Five is represented by narrative planning features. We also present a study to evaluate whether human readers can perceive the modeled personality traits through simple action patterns in short stories.