Artificial Intelligence techniques have been successfully applied to several computer games. However in some kinds of computer games, like real-time strategy (RTS) games, traditional artificial intelligence techniques fail to play at a human level because of the vast search spaces that they entail. In this paper we present a real-time case based planning and execution approach designed to deal with RTS games. We propose to extract behavioral knowledge from expert demonstrations in form of individual cases. This knowledge can be reused via a case based behavior generator that proposes behaviors to achieve the specific open goals in the current plan. Specifically, we applied our technique to the WARGUS domain with promising results.
Read the paper:
Case-Based Planning and Execution for Real-Time Strategy Games
by Santi Ontañón, Kinshuk Mishra, Neha Sugandh, Ashwin Ram
Seventh International Conference on Case-Based Reasoning (ICCBR-07), Belfast, Northern Ireland, August 2007www.cc.gatech.edu/faculty/ashwin/papers/er-07-11.pdf
View my profile.svg){kind=logo}
Read my bio
Follow me
OpenStudy with me
Cognitive Computing 
Posted by santi on October 13, 2009 at 5:32 pm
Alex J. Champandard, from AIGameDev.com overviewed the Darmok system, presented in this paper. The review rises interesting points, and reveals which points the industry considers as valuable and which ones are seen as drawbacks. It is specially interesting that they coinsidered our Darmok system as the system of their choice to illustrate CBR applied fo computer games: http://aigamedev.com/editorial/critique-case-based-reasoning