EvolvingBehavior: Towards Co-Creative Evolution of Behavior Trees for Game NPCs
Partlan, Nathan, Soto, Luis, Howe, Jim, Shrivastava, Sarthak, El-Nasr, Magy Seif, Marsella, Stacy
–arXiv.org Artificial Intelligence
To assist game developers in crafting game NPCs, we present EvolvingBehavior, a novel tool for genetic programming to evolve behavior trees in Unreal Engine 4. In an initial evaluation, we compare evolved behavior to hand-crafted trees designed by our researchers, and to randomly-grown trees, in a 3D survival game. We find that EvolvingBehavior is capable of producing behavior approaching the designer's goals in this context. Finally, we discuss implications and future avenues of exploration for co-creative game AI design tools, as well as challenges and difficulties in behavior tree evolution.
arXiv.org Artificial Intelligence
Sep-1-2022
- Country:
- North America
- United States
- New York > New York County
- New York City (0.04)
- Massachusetts
- Suffolk County > Boston (0.04)
- Middlesex County > Natick (0.04)
- California > Santa Cruz County
- Santa Cruz (0.14)
- New York > New York County
- Canada > Quebec
- Montreal (0.14)
- United States
- Europe
- North America
- Genre:
- Research Report
- Experimental Study (0.68)
- New Finding (0.68)
- Research Report
- Industry:
- Information Technology > Software (1.00)
- Health & Medicine (0.93)
- Leisure & Entertainment > Games
- Computer Games (1.00)
- Technology: