Learning in Multi-Robot Systems

Maja J Mataric
Volen Center for Complex Systems
Computer Science Department
Brandeis University
Waltham, MA 02254
tel: (617) 736-2708
fax: (617) 736-2741
maja@cs.brandeis.edu

Abstract

This paper discusses why traditional reinforcement learning
methods, and algorithms applied to such theoretical models, often
result in poor performance in dynamic, situated multi--agent
domains characterized by multiple goals, noisy perception and
action, and inconsistent reinforcement.  We propose a methodology
for designing the representation and the forcement functions that
take advantage of implicit domain knowledge in order to accelerate
learning in such domains, and demonstrate it experimentally in two
different mobile robot domains.