This page is a chronological list (with most recent entries first) of researchers and publications that have been added.
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.
Research interests: Distributed and Multi-Agent RL | Collaborative Reinforcement Learning | Distributed Systems with Reinforcement Learning |
E-mail: jdowling@sics.se
Home page: http://www.jimdowling.info/
Efficient Structure Learning in Factored-state MDPs
AAAI 2007 (PDF - 115KB) Abstract:
We consider the problem of reinforcement learning in factored-state MDPs in the setting in which le...
Borkar, Vivek with: Tata Institute of Fundamental Research, Mumbai, India
Research interests: Function approximation | Hierarchical methods | Partially-observable problems | TD-learning | Average-reward/undiscounted methods | DP/MDP | Theoretical analysis | Distributed and Multi-Agent RL |
E-mail: borkar@tifr.res.in
Home page: http:// www.tcs.tifr.res.in/~borkar/PersonalPage.html
Bianchi, Reinaldo A. C. with: Centro Universit to robotics | DP/MDP | Theoretical analysis | Distributed and Multi-Agent RL |
E-mail: rbianchi@fei.edu.br
Home page: http://www.fei.edu.br/~rbianchi
Melo, Francisco with: Institute for Systems and Robotics, Portugal
Research interests: Function approximation | Applications to robotics | Partially-observable problems | TD-learning | DP/MDP | Theoretical analysis | Distributed and Multi-Agent RL |
E-mail: fmelo@isr.ist.utl.pt
Nearly optimal exploration-exploitation decision thresholds
ICANN 2006 ( gzipped Postscript - 170Kb) Abstract:
While in general trading off exploration and exploitation in reinforcement learning is hard, under ...
Laurent, Guillaume with: Laboratoire d'Automatique de Besans | DP/MDP |
E-mail: yvantv@ele.puc-rio.br
Home page: http://www.ica.ele.puc-rio.br
Tc.ir>rahimian@comp.iust.ac.ir
Temporal sequence learning, prediction and control - A review of different models and their relation to biological mechanisms
Neural Computation, 17: 245-319 Abstract:
A review of RL in view of its relation to classical conditioning and the biophysics of the underlyin...
Woergoetter, Florentin with: University of Goettingen
Research interests: Applications to robotics | Planning | Neuro-biological RL | Theoretical analysis | Distributed and Multi-Agent RL |
E-mail: worgott@chaos.gwdg.de
Home page: http://www.ifi.informatik.uni-goettingen.de/staff/florentin_woergoetter.html
Clinical data based optimal STI strategies for HIV: a reinforcement learning approach
Proceedings of Benelearn 2006, 11-12 May 2006, Ghent, Belgium (pdf - 172 KB) Abstract:
This paper addresses the problem of computing optimal structured treatment interruption strategies f...
Cuayverage-reward/undiscounted methods | Distributed and Multi-Agent RL |
E-mail: gaoy@nju.edu.cn
Home page: http://cs.nju.edu.cn/gaoy
Dimitrakakis, Christos with: IDIAP
Research interests: Function approximation | Partially-observable problems | Planning | Neuro-biological RL | Theoretical analysis | Distributed and Multi-Agent RL |
E-mail: dimitrak@idiap.ch
Home page: http://www.idiap.ch/~dimitrak
Gradient Estimates of Return
IDIAP Research Report (abridged version presented at PASCAL workshop on principled methods of trading exploration and exploitation) ( gzipped Postscript - 185KB) Abstract:
The exploration-exploitation trade-off that arises when one considers simple point estimates of exp...
Mahmood, Tariq with: ITC-IRST, Trento, Italy
Research interests: Function approximation | Partially-observable problems | DP/MDP |
E-mail: tariq@itc.it
Fathzadeh, Ramin with: Qazvin Azad University
Research interests: Applications to robotics | Average-reward/undiscounted methods | Planning | Distributed and Multi-Agent RL |
E-mail: ramin_ftz@yahoo.com
Munoz de Cote, Enrique with: Politecnico di Milano
Research interests: Distributed and Multi-Agent RL |
E-mail: munoz@elet.polimi.it
Home page: http://www.elet.polimi.it/upload/munoz/
Coquelin, Pierre-Arnaud with: CMAP, ttp://www.cmap.polytechnique.fr/~coquelin/index.html>http://www.cmap.polytechnique.fr/~coquelin/index.html
Ahn, Hyungil with: MIT Media Lab
Research interests: Hierarchical methods | Partially-observable problems | Planning | Neuro-biological RL |
E-mail: hiahn AT media DOT mit DOT edu
Home page: http://web.media.mit.edu/~hiahn
Selecting concise sets of samples for a reinforcement learning agent
Conference Proceedings of CIRAS 2005 (pdf - 1036 KB) Abstract:
We derive an algorithm for selecting from the set of samples gathered by a reinforcement learning a...
Model Free Intelligent Control Using Reinforcement Learning and Temporal Abstraction-applied to pH Control.
IFAC 2005 (pdf - 300) Abstract:
This article presents a solution to pH control based on model-free intelligent control (MFIC) using ...
Syam, Syafiie with: University of Valladolid, Spain
Research interests:
E-mail: syam@autom.uva.es
Home page: http://www.isa.cie.uva.es/~syam/
Mariano, Carlos with: Mexican Institute for Water Technology
Research interests: Function approximation | TD-learning | Average-reward/undiscounted methods | Distributed and Multi-Agent RL |
E-mail: cmariano@tlaloc.imta.mx
Home page: http://www.imta.mx
Hwang, Kao-Shing with: National Chung Cheng Univ.
Research interests: Applications to robotics | TD-learning | Neuro-biological RL | Distributed and Multi-Agent RL |
E-mail: hwang@ccu.edu.tw
Home page: http://www.eis.ee.ccu.edu.tw/~hwang
Brain Inspired Reinforcement Learning
NIPS 2004 (NIPS 17) Abstract:
Successful application of reinforcement learning algorithms often involves considerable hand-craftin...
Combining TD-learning with Cascade-correlation Networks
ICML 2003 Abstract:
Using neural networks to represent value functions in reinforcement learning algorithms often invo...
Rivest, Francois with: Universit:
Ganesan, Rajesh with: Gorge Mason University
Research interests: Function approximation | Hierarchical methods | DP/MDP |
E-mail: rganesan@gmu.edu
Home page: http://mason.gmu.edu/~rganesan
9/20/2005 - New Researcher Added:
Elhanany, Itamar with: The University of Tennessee
Research interests: Applications to robotics | Partially-observable problems | TD-learning |
E-mail: itamar@ieee.org
Home page: http://www.ece.utk.edu/~itamar
9/14/2005 - New Researcher Added:
PHOMPHEEPHAK, Phonevixay with: KHON KHAEN UNIVERSITY (THAILAND)
Research interests:
E-mail: pvxp0@yahoo.com
8/9/2005 - New Publication Added:
Ernst, Damien , Pierre Geurts, Mevludin Glavic, Louis Wehe