Construction of a memory management system in an on-line learning mechanism

This paper is the first of a two paper series that deals with an important problem in on-line learning mechanisms for autonomous agents that must perform non trivial tasks and operate over extended periods of time. The problem has to do with memory, and, in particular, with what is to be stored in what representation and the need for providing a memory management system to control the interplay between different types of memory. To study the problem, a two level memory structure consisting of a short term and a long term memory is introduced in an evolutionary based cognitive mechanism called the Multilevel Darwinist Brain. A management system for their operation and interaction is proposed that benefits from the evolutionary nature of the mechanism. Some results obtained during operation with real robots are presented in the second paper of the series.

• Type: Conference
• Year: 2006
• Where: ESANN
• Authors: Francisco Bellas, José Antonio Becerra, Richard J. Duro
• Keywords: ESANN 2006, ESANN 2007, Level Memory Structure, Long Term Memory, Non Trivial Tasks