Towards Adaptability of Demonstration-Based Training of NPC Behavior

Authors

  • John Drake University of Pennsylvania
  • Alla Safonova University of Pennsylvania
  • Maxim Likhachev Carnegie Mellon University

DOI:

https://doi.org/10.1609/aiide.v13i1.12949

Keywords:

planning, graph search, NPC behavior, search-based planning, behavior training, behavior demonstration

Abstract

Using demonstration to guide behavior generation for non-player characters (NPCs) is a challenging problem. Particularly, as new situations are encountered, demonstration records often do not closely correspond with the task at hand. Open-world games such as The Elder Scrolls V: Skyrim or Borderlands often reuse locations within the game world for multiple quests. In each new quest at each location, the particular configuration of game elements such as health packs, weapons, and enemies changes. In this paper, we present an approach that utilizes user demonstrations for generating NPC behaviors while accommodating such variations in the game configuration across quests.

Downloads

Published

2021-06-25

How to Cite

Drake, J., Safonova, A., & Likhachev, M. (2021). Towards Adaptability of Demonstration-Based Training of NPC Behavior. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 13(1), 179-185. https://doi.org/10.1609/aiide.v13i1.12949