|
Published Articles >> Table of Contents >> Abstract
Third International Joint Conference on Autonomous Agents and Multiagent Systems - Volume 3 (AAMAS'04)
pp. 1122-1129
Multi-Agent Patrolling with Reinforcement Learning
Hugo Santana, Universidade Federal de Pernambuco
Geber Ramalho, Universidade Federal de Pernambuco
Vincent Corruble, Université Paris 6
Bohdana Ratitch, McGill University
Full Article Text:
 
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/AAMAS.2004.10176
Send link to a friend
| Abstract |
|
Patrolling tasks can be encountered in a variety of
real-world domains, ranging from computer network
administration and surveillance to computer wargame
simulations. It is a complex multi-agent task, which
usually requires agents to coordinate their decision-making
in order to achieve optimal performance of the
group as a whole. In this paper, we show how the
patrolling task can be modeled as a reinforcement
learning (RL) problem, allowing continuous and
automatic adaptation of the agents’ strategies to their
environment. We demonstrate that an efficient
cooperative behavior can be achieved by using RL
methods, such as Q-Learning, to train individual agents.
The proposed approach is totally distributed, which
makes it computationally efficient. The empirical
evaluation proves the effectiveness of our approach, as
the results obtained are substantially better than the
results available so far on this domain.
|
 Additional Information
|
Citation:
Hugo Santana, Geber Ramalho, Vincent Corruble, Bohdana Ratitch,
"Multi-Agent Patrolling with Reinforcement Learning,"
aamas,
pp. 1122-1129,
Third International Joint Conference on Autonomous Agents and Multiagent Systems - Volume 3 (AAMAS'04),
2004
|
|
