PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Cooperative Information Sharing to Improve Distributed Learning
Partha Dutta, Srinandan Dasmahapatra, Steve Gunn, Nick Jennings and Luc Moreau
In: AAMAS 2004 Workshop on Learning and Evolution in Agent-Based Systems, New York, USA(2004).

Abstract

Effective coordination in partially observable MAS requires agent actions to be based on reliable estimates of non-local states. One way of generating such estimates is to allow the agents to share state information that is not directly observable. To this end, we propose a novel strategy of delayed distribution of state estimates. Our empirical studies of this mechanism demonstrate that individual reinforcement-learning agents in a simulated network routing problem achieve a significant improvement in the overall success, robustness, and efficiency of routing compared with the standard Q-routing algorithm.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:851
Deposited By:Steve Gunn
Deposited On:01 January 2005