ADPRL 2013

2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning

Adaptive (or Approximate) dynamic programming (ADP) is a general and effective approach for solving optimal control problems by adapting to uncertain environments over time. ADP optimizes a user-defined cost function with respect to an adaptive control law, conditioned on prior knowledge of the system, and its state, in the presence of system uncertainties. A numerical search over the present value of the control minimizes a nonlinear cost function forward-in-time providing a basis for real-time, approximate optimal control. The ability to improve performance over time subject to new or unexplored objectives or dynamics has made ADP an attractive approach in a number of application domains including optimal control and estimation, operation research, and computational intelligence. ADP is viewed as a form of reinforcement learning based on an actor-critic architecture that optimizes a user-prescribed value online and obtains the resulting optimal control policy.
Reinforcement learning (RL) algorithms learn to optimize an agent by letting it interact with an environment and learn from its received feedback. The goal of the agent is to optimize its accumulated reward over time, and for this it estimates value functions that predict its future reward intake when executing a particular policy. Reinforcement learning techniques can be combined with many different function approximators and do not assume any a priori knowledge about the environment. An important aspect in RL is that an agent has to explore parts of the environment it does not know well, while at the same time it has to exploit its knowledge to maximize its reward intake. RL techniques have already been applied successfully for many problems such as controlling robots, game playing, elevator control, network routing, and traffic light optimization.


The symposium topics include, but are not limited to:

Keynote, Tutorial and Panel Sessions

Please forward your proposals with detailed abstract and bio-sketches of the speakers to Symposium Co-Chairs and SSCI Keynote-Tutorial Chair, Dr S Das.

Accepted Special Sessions

Special Session 1:  Online planning
Organizers:  Lucian Busoniu ] and Rémi Munos
 (To submit a paper to this session, please select "01s1" as the main research topic)



Special Session 2: Evolutionary Algorithms for ADPRL

Organizers: Hisashi Handa ]   &  Kazuhiro Ohkura
 (To submit a paper to this session, please select "01s2" as the main research topic)


Special Session 3:  Finite-Approximate-Error Based Adaptive Dynamic Programming: Algorithms and Applications
Organizers: Yanhong Luo, ],  Qinglai Wei and Zengguang Hou (To submit a paper to this session, please select "01s3" as the main research topic)


Special Session 4:  Data-driven Adaptive Dynamic Programming and Its Applications in Complex Systems
Organizers: Derong Liu, Haibo He ]  and Dongbin Zhao
 (To submit a paper to this session, please select "01s4" as the main research topic)

Special Session 5:  Special session on ADP and RL in real-time feedback systems
Organizers:  Xin Xu ]  &   Haibo He. 
(To submit a paper to this session, please select "01s5" as the main research topic)


Special Sessions

Please forward your special session proposals to Symposium Co-Chairs.

Symposium Chair

Marco Wiering, University of Groningen, Netherlands

Symposium Co-Chairs

Jagannathan Sarangapani, Missouri University of Science and Technology, USA

Huaguang Zhang, Northeastern University, China

Program Committee

Robert Babuska Delft University of Technology, Netherlands
El-Sayed Mohamed El-Alfy King Fahd University of Petroleum and Minerals, Saudi Arabia
Abhijit Gosavi Missouri University of Science and Technology, USA
Frank L. Lewis University of Texas at Arlington, USA
Haibo He University of Rhode Island, USA
Warren Powell Princeton University, USA
 Jennie Si  Arizona State University, USA
Danil Prokhorov Toyota Technical Center, USA
Shimon Whiteson University of Amsterdam, Netherlands
Charles W. Anderson Colorado State University, USA
Matteo Gagliolo Vrije Universiteit Brussel, Belgium
Hisashi Handa Okayama University, Japan
Dong-Bin Zhao Chinese Academy of Sciences, China
Kazuhiro Ohkura Hiroshima University, Japan
Damien Ernst University of Liege, Belgium
Lucian Busoniu University of Lorraine, France
Zhong-Ping Jiang Polytechnic Institute of NYU, USA
Marcus Hutter Australian National University, Australia
Yasutake TAKAHASHI University of Fukui, Japan
Derong Liu University of Illinois Chicago, USA
Koichi Moriyama Osaka University, Japan
Emo Todorov University of Washington,USA
Yanhong Luo Northeastern University, China
Ann Nowé Vrije Universiteit Brussel, Belgium
Zeng-Guang Hou Chinese Academy of Sciences, China
Rémi Munos INRIA Lille - Nord Europe, France
Draguna Vrabie United Technologies Research Center, USA
Xin Xu National University of Defense Technology, China
Yan Zhao Shenyang Institute of Engineering,  China
Dedong Yang Hebei University of Technology
Tiedong Ma Chongqing University, China
Xin Zhang Northeastern University, China
Raphael Fonteneau University of Liege, Belgium
Antonios Tsourdos Defence Academy of the United Kingdom
Mingcong Deng Tokyo University, Japan
Hossein Javaherian General motors Warren, USA
Martijn van Otterlo Radboud University Nijmegen, Netherlands
Harm van Seijen University of Alberta, Canada
Hado van Hasselt CWI Amsterdam, Netherlands
Marc Deisenroth University of Washington,USA 
Gerhard Neuman Technical University Darmstadt, Germany
Abdeslam Boularias Max Planck Institute for Intelligent Systems Tübingen, Germany
Frans Oliehoek University of Maastricht. Netherlands
Nikos Vlassis University of Luxembourg
Matthijs Spaan Delft University of Technology, Netherlands
Martin Riedmiller University of Freiburg, Germany
Thomas Gabel University of Freiburg, Germany
Todd Hester University of Austin, Texas, USA
Karl Tuyls University of Maastricht. Netherlands
Istvan Szita Google. Switzerland
Shahab Mehraeen Louisiana State University
Travis Dierks DRS Technologies, St. Louis
Kyriakos Vamvoudakis University of California
Guang-Bin Huang Nanyang Technological University, Singapore
Jian Fu Wuhan University of Technology, China
Zhanshan Wang Northeastern University, China
Qinglai Wei Chinese Academy of Sciences, China
Chunbin Qin Henan University, China
Itamar Arel University of Tennessee, USA