Case-Based Planning and Execution

[Kyran]

A paper by Santiago Ontanon, Kinshuk Mishra, Neha Sugandh, and Ashwin Ram.

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.

[Kyran]

This paper is particularly interesting to me because it copies the strategies of the human players (rather then just trial and erroring it). I've got an idea for a new AI that will be useful for creating campaigns.