Conroy, Ross, Zeng, Yifeng, Cavazza, Marc ORCID: https://orcid.org/0000-0001-6113-9696 and Chen, Yingke (2015) Learning behaviors in agents systems with interactive dynamic influence diagrams. In: Proceedings of the 24th International Conference on Artificial Intelligence (IJCAI'15). AAAI Press, pp. 39-45. ISBN 978-1-57735-738-4

Full text not available from this repository.

Abstract

Interactive dynamic influence diagrams (I-DIDs) are a well recognized decision model that explicitly considers how multiagent interaction affects individual decision making. To predict behavior of other agents, I-DIDs require models of the other agents to be known ahead of time and manually encoded. This becomes a barrier to I-DID applications in a human-agent interaction setting, such as development of intelligent non-player characters (NPCs) in real-time strategy (RTS) games, where models of other agents or human players are often inaccessible to domain experts. In this paper, we use automatic techniques for learning behavior of other agents from replay data in RTS games. We propose a learning algorithm with improvement over existing work by building a full profile of agent behavior. This is the first time that data-driven learning techniques are embedded into the I-DID decision making framework. We evaluate the performance of our approach on two test cases.

Item Type:	Conference Proceedings
Title of Proceedings:	Proceedings of the 24th International Conference on Artificial Intelligence (IJCAI'15)
Additional Information:	Conference held in Buenos Aires, Argentina from 25-31 July, 2015
Uncontrolled Keywords:	Interactive dynamic influence diagrams (I-DIDs); Learning algorithms; Data-driven learning techniques
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Faculty / School / Research Centre / Research Group:	Faculty of Engineering & Science > School of Computing & Mathematical Sciences (CMS) Faculty of Engineering & Science
Last Modified:	04 Mar 2022 13:07
URI:	http://gala.gre.ac.uk/id/eprint/19809

Actions (login required)

View Item