Combining attention and value maps

Authors:
Stathis Kasderidis;John G. Taylor
Affiliations:
Foundation for Research and Technology – Hellas, Institute of Computer Science, Heraklion, Greece;Dept. of Mathematics, King’s College, London, UK
Venue:
ICANN'05 Proceedings of the 15th international conference on Artificial Neural Networks: biological Inspirations - Volume Part I
Year:
2005

Citing 3
Cited 4

Reinforcement Learning

Reinforcement Learning
Machine Learning

Machine Learning
Attentional Agents and robot control

International Journal of Knowledge-based and Intelligent Engineering Systems - Advanced Intelligent Techniques in Engineering Applications

2006 Special Issue: Attention as a controller

Neural Networks
Towards a control theory of attention

ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part II
A review of cognitive processing in the brain

ICANN'05 Proceedings of the 15th international conference on Artificial Neural Networks: biological Inspirations - Volume Part I
A computational model for multiple goals

ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present an approach where we combine attention with value maps for the purpose of acquiring a decision-making policy for multiple concurrent goals. The former component is essential for dealing with an uncertain and open environment while the latter offers a general model for building decision-making systems based on reward information. We discuss the multiple goals policy acquisition problem and justify our approach. We provide simulation results that support our solution.