Limitations of Choice-Based Interactive Evolution for Game Level Design

Authors

  • Antonios Liapis IT University of Copenhagen
  • Georgios Yannakakis IT University of Copenhagen
  • Julian Togelius IT University of Copenhagen

DOI:

https://doi.org/10.1609/aiide.v8i5.12571

Keywords:

procedural content generation, choice-based interactive evolution, human-based computation, constrained optimization, game level design

Abstract

This paper presents a tool geared towards the collaboration of a human and an artificial designer for the creation of game content. The framework combines procedural content generation using stochastic search with user input in the form of an initial goal statement as well as preference of generated results. Feedback from industry experts in a pilot user experiment showcased the limitations of this approach and the protocol chosen for evaluating the authoring tool. The limitations are discussed with respect to the suitability of interactive evolution for creative design and the design of experimental protocols for evaluating authoring tools for games.

Downloads

Published

2021-06-30

How to Cite

Liapis, A., Yannakakis, G., & Togelius, J. (2021). Limitations of Choice-Based Interactive Evolution for Game Level Design. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 8(5), 33-36. https://doi.org/10.1609/aiide.v8i5.12571