Publications on Distributed and Multi-Agent RL
Dowling, Jim , Eoin Curran, Raymond Cunningham, Vinny Cahill (email@example.com)
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).
Dowling, Jim , Seif Haridi (firstname.lastname@example.org)
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,
, Maja Mataric( email@example.com)
Coordinating Mobile Robot Group Behavior Using a Model of Interaction Dynamics
( gzipped Postscript - 263 KB)
In this paper we show how various levels of coordinated behavior may
be achieved in a group of mob...
, E. J. Collins
Individual Q-learning in normal form games
(PDF - 210K)
The single-agent multi-armed bandit problem can be solved by an
agent that learns the values of e...
Learning Multi-Agent Search Strategies
The Interdisciplinary Journal of Artificial Intelligence and the Simulation of Behaviour, 1(4), 2003.
(pdf - 305KB)
We identify a specialised class of reinforcement learning problem in which the agent(s) have the goa...
, Jafar Adibi, Yaser Al-Onaizan, Ali Erdem, Gal Kaminaka, Stacy Marsella, Ion Muslea, Marcello Tallis( firstname.lastname@example.org)
Building Agent Teams Using an Explicit Teamwork Model and Learning
Artificial Intelligence 1999
(Postscript - 790 KB)
Multi-agent collaboration or teamwork and learning are two critical research challenges in a large
, John M. Dolan, Pradeep K. Khosla
The Necessity of Average Rewards in Cooperative Multirobot Learning
(pdf - 176KB)
Learning can be an effective way for robot systems to deal with dynamic environments and changing ta...
, David Wolpert( email@example.com)
Collective Intelligence and Braess' Paradox
To appear in AAAI 2000 in Austin, Tx
(Postscript - 330 KB)
We consider the use of multi-agent systems to control network routing. Conventional
approaches to ...
, William Uther, Masahiro Fujita, Minoru Asada, Hiroaki Kitano( firstname.lastname@example.org)
Playing Soccer with Legged Robots
Proceedings of IROS-98, Intelligent Robots and Systems Conference
( PDF - 278 KB)
Sony has provided a remarkable platform for research and development in robotic agents, namely fully...
, Sridhar Mahadevan( email@example.com)
Hierarchical Optimization of Policy-Coupled Semi-Markov Decision Processes
International Conference on Machine Learning (ICML-99)
( gzipped Postscript - 250)
Manufacturing is a challenging real-world domain for applying
MDP-based reinforcement learning algo...
, Kagan Tumer( firstname.lastname@example.org)
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)
This paper introduces the concept of ``COllective INtelligence'' (COIN). A COIN is a large
, Kevin Wheeler and Kagan Tumer( email@example.com)
Collective Intelligence for Control of Distributed Dynamical
Europhysics Letters , Vol. 49, No. 6, March 2000.
(Postscript - 350KB)
We consider the El Farol bar problem (W. B. Arthur, The American Economic Review , 84(2): 406--411 (...
, samuel delepoulle, jean-claude darcheville
A Generic architecture for Adaptive Agents Based on Reinforcement Learning
Information Sciences Journal
In this paper, we present MAABAC, a generic model for building adaptive agents: they learn new behav...