Selecting Agents for Narrative Roles

Authors

  • Alexander Shoulson University of Pennsylvania
  • Daniel Garcia University of Pennsylvania
  • Norman Badler University of Pennsylvania

DOI:

https://doi.org/10.1609/aiide.v7i2.12457

Keywords:

Interactive Narrative, Smart Events, Behavioral AI, Agents

Abstract

We present ongoing work on a system that accommodates player agency in a digital narrative with an external plot. We focus on key events that should occur in that storyline for dramatic effect, but do not explicitly specify the characters that should fill the roles needed for those events. Instead, we define them abstractly, with characteristics that the selected characters should have (including previous events they should have completed for eligibility), and rely on a Director construct to populate those roles from agents in the selection pool that fit those criteria. Agents begin as largely homogeneous, primordial entities that accumulate data and narrative value from the events in which they participate. This creates an environment that differentiates characters by the actions they perform, conferring worth onto characters that become important to the player based on their direct involvement in the plot. The focus, then, is on defining a priori the what of the narrative, while leaving it to the Director construct to decide at runtime exactly who among a distributed pool of agents carries it out.

Downloads

Published

2011-10-09

How to Cite

Shoulson, A., Garcia, D., & Badler, N. (2011). Selecting Agents for Narrative Roles. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 7(2), 65-68. https://doi.org/10.1609/aiide.v7i2.12457