An episodic memory implementation for a virtual creature

Ricardo Ribeiro Gudwin

pp. 393-406

in: Lorenzo Magnani, Walter Carnielli, Claudio Pizzi (eds), Model-based reasoning in science and technology, Berlin, Springer, 2010

Abstract

This work deals with the research on intelligent virtual creatures and cognitive architectures to control them. Particularly, we are interested in studying how the use of episodic memory could be useful to improve a cognitive architecture in such a task. Episodic memory is a neurocognitive mechanism for accessing past experiences that naturally makes part of human process of decision making, which usually enhances the chances of a successful behavior. Even though there are already some initiatives in such a path, we are still very far from this being a well known technology to be widely embedded in our intelligent agents. In this work we report on our ongoing efforts to bring up such technology by building up a cognitive architecture where episodic memory is a central capability.