Exploring the Space of Computational Memory Models

Abstract

Over their lifetimes, intelligent agents gain knowledge that may be pertinent to their decisions about acting in the world. One goal of memory system research is to develop an optimal set of encoding, storage, and retrieval mechanisms that will harness these experiences to facilitate rational decisions. In this paper, we propose a direction of empirical, computational research that seeks to better understand the behavioural dynamics that arise when an agent endowed with long-term memory is situated in a task, by determining which properties of task and characteristics of memory systems in combination are responsible for which aspects of behaviour.We propose preliminary taxonomies for task and memory spaces, and also propose metrics for systematic evaluation of memory systems.

2 Figures and Tables

Cite this paper

@inproceedings{Derbinsky2010ExploringTS, title={Exploring the Space of Computational Memory Models}, author={Nate Derbinsky and Nicholas A. Gorski}, year={2010} }