|
Adaptive Objective Selection for Correlated Objectives in Multi-Objective Reinforcement Learning Host Publication: 13th International Conference on Autonomous Agents and Multi-Agent Systems, AAMAS 2014 Authors: T. Brys, K. Marguerite Van Moffaert, A. Nowé and M. Taylor UsePubPlace: Paris, France Publisher: ACM Publication Year: 2014 Number of Pages: 2 ISBN: 978-1-4503-2738-1
Abstract: In this paper we introduce a novel scale-invariant and parameterless technique, called adaptive objective selection, that allows a temporal-difference learning agent to exploit the correlation between objectives in a multi-objective problem. It identifies and follows in each state the objective whose estimates it is most confident about. We propose several variants of the approach and empirically demonstrate it on a toy problem. External Link.
|
