Publications on Distributed and Multi-Agent RL

Using Feedback in Collaborative Reinforcement Learning to Adaptively Optimise MANET Routing
IEEE Transactions on Systems, Man and Cybernetics (Part A), Special Issue on Engineering Self-Orangized Distributed Systems, vol. 35, no. 3, pages 360-372, May 2005.
Abstract: This work describes a decentralized, multi-agent learning algorithm, called collaborative reinforcement learning and demonstrates how it can be used to optimize the system properties (e.g., throughput) of a routing algorithm for Mobile Ad Hoc Networks (MANETs).

Decentralized Reinforcement Learning for the Online Optimization of Distributed Systems
Chapter in Reinforcement Learning: Theory and Applications, Advanced Robotic Systems Journal, Editors Cornelius Weber, Mark Elshaw and Norbert Michael Mayer. I-Tech Education and Publishing, ISBN 978-3-902613-14-1, 2008: 142-167.

Coordinating Mobile Robot Group Behavior Using a Model of Interaction Dynamics
unpublished ( gzipped Postscript - 263 KB) Abstract:
In this paper we show how various levels of coordinated behavior may be achieved in a group of mob...

E-mail: dleslie@stats.ox.ac.uk
Individual Q-learning in normal form games
unpublished (PDF - 210K) Abstract:
The single-agent multi-armed bandit problem can be solved by an agent that learns the values of e...

E-mail: mjstrens@qinetiq.com
Learning Multi-Agent Search Strategies
The Interdisciplinary Journal of Artificial Intelligence and the Simulation of Behaviour, 1(4), 2003. (pdf - 305KB) Abstract:
We identify a specialised class of reinforcement learning problem in which the agent(s) have the goa...

Building Agent Teams Using an Explicit Teamwork Model and Learning
Artificial Intelligence 1999 (Postscript - 790 KB) Abstract:
Multi-agent collaboration or teamwork and learning are two critical research challenges in a large ...

E-mail: pojt@cmu.edu
The Necessity of Average Rewards in Cooperative Multirobot Learning
ICRA 2002 (pdf - 176KB) Abstract:
Learning can be an effective way for robot systems to deal with dynamic environments and changing ta...

Collective Intelligence and Braess' Paradox
To appear in AAAI 2000 in Austin, Tx (Postscript - 330 KB) Abstract:
We consider the use of multi-agent systems to control network routing. Conventional approaches to ...

Playing Soccer with Legged Robots
Proceedings of IROS-98, Intelligent Robots and Systems Conference ( PDF - 278 KB) Abstract:
Sony has provided a remarkable platform for research and development in robotic agents, namely fully...

Hierarchical Optimization of Policy-Coupled Semi-Markov Decision Processes
International Conference on Machine Learning (ICML-99) ( gzipped Postscript - 250) Abstract:
Manufacturing is a challenging real-world domain for applying MDP-based reinforcement learning algo...

An introduction to Collective Intelligence
NASA tech rep NASA-ARC-IC-99-63, (to appear in J. M. Bradshaw, ed, handbook on agent technology) (Postscript - 1.4 MB) Abstract:
This paper introduces the concept of ``COllective INtelligence'' (COIN). A COIN is a large multi-a...

Collective Intelligence for Control of Distributed Dynamical Systems
Europhysics Letters , Vol. 49, No. 6, March 2000. (Postscript - 350KB) Abstract:
We consider the El Farol bar problem (W. B. Arthur, The American Economic Review , 84(2): 406--411 (...

E-mail: philippe.preux@univ-lille3.fr
A Generic architecture for Adaptive Agents Based on Reinforcement Learning
Information Sciences Journal Abstract:
In this paper, we present MAABAC, a generic model for building adaptive agents: they learn new behav...