Learning Control for an Xpilot-AI Agent Playing Capture the Flag-Reference-Cited by-同舟云学术

Learning Control for an Xpilot-AI Agent Playing Capture the Flag

Published:2012-01 Issue:1 Volume:3 Page:1-12
ISSN:1947-9344
Container-title:International Journal of Organizational and Collective Intelligence
language:en
Short-container-title:

Author:

Parker Gary¹,Penrose Sarah¹

Affiliation:

1. Department of Computer Science, Connecticut College, New London, CT, USA

Abstract

Xpilot-AI is an environment where researchers can test autonomous agent control and learning programs. It is based on Xpilot, which is an open source, 2d space combat game. Xpilot-AI allows a programmer to write scripts that control an agent playing a game of Xpilot. In previous work, a wide range of techniques have been used to develop controllers that are focused on the combat skills for an Xpilot agent. In this research, a Genetic Algorithm (GA) was used to evolve the parameters for an expert agent solving the more challenging problem of capture the flag.

Publisher

IGI Global

Reference12 articles.

1. Allen, M., Dirmaier, K., & Parker, G. (2010. Real-time AI in Xpilot using reinforcement learning. In Proceedings of the 2010 World Automation Congress International Symposium on Intelligent Automation and Control (ISIAC 2010).

2. Combining AI methods for learning bots in a real-time strategy game.;R.Baumgarten;International Journal of Computer Games Technology,2009

3. Ciesielski, V., & Lai, S. (2001). Developing a dribble-and-score behaviour for robot soccer using neuro evolution. In Proceedings of the 5th Australia-Japan Joint Workshop on Intelligent and Evolutionary Systems.

4. Li, X., Wang, M., & Zell, A. (2007). Dribbling control of omnidirectional soccer robots. In Proceedings of the 2007 IEEE International Conference on Robotics and Automation.

5. Luke, S. (1998). Genetic programming produced competitive soccer softbot teams for RoboCup97. In Proceedings of Genetic Programming 1998.