Constructing Game Agents from Video of Human Behavior

Authors

  • Nan Li School of Computing and Informatics, Arizona State University
  • David Stracuzzi School of Computing and Informatics, Arizona State University
  • Gary Cleveland School of Computing and Informatics, Arizona State University
  • Tolga Konik Computational Learning Laboratory, Stanford University
  • Dan Shapiro Computational Learning Laboratory, Stanford University
  • Matthew Molineaux Knexus Research
  • David Aha Naval Research Laboratory
  • Kamal Ali Computational Learning Laboratory, Stanford University

Abstract

Developing computer game agents is often a lengthy and expensive undertaking. Detailed domain knowledge and decision-making procedures must be encoded into the agent to achieve realistic behavior. In this paper, we simplify this process by using the ICARUS cognitive architecture to construct game agents. The system acquires structured, high fidelity methods for agents that utilize a vocabulary of concepts familiar to game experts. We demonstrate our approach by first acquiring behaviors for football agents from video footage of college football games, and then applying the agents in a football simulator.

Downloads

Published

2009-10-16

How to Cite

Li, N., Stracuzzi, D., Cleveland, G., Konik, T., Shapiro, D., Molineaux, M., Aha, D., & Ali, K. (2009). Constructing Game Agents from Video of Human Behavior. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 5(1), 64-69. Retrieved from https://ojs.aaai.org/index.php/AIIDE/article/view/12356