Click here for Symposium website
Adaptive dynamic programming (ADP) and reinforcement learning (RL) are two related paradigms for solving decision making problems where a performance index must be optimized over time. ADP and RL methods are enjoying a growing popularity and success in applications, fueled by their ability to deal with general and complex problems, including features such as uncertainty, stochastic effects, and nonlinearity.
ADP tackles these challenges by developing optimal control methods that adapt to uncertain systems over time. A user-defined cost function is optimized with respect to an adaptive control law, conditioned on prior knowledge of the system and its state, in the presence of 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 successful in applications from optimal control and estimation, operation research, and computational intelligence.
RL takes the perspective of an agent that optimizes its behavior by interacting with its environment and learning from the feedback received. The long-term performance is optimized by learning a value function that predicts the future intake of rewards over time. A core feature of RL is that it does not require any a priori knowledge about the environment. Therefore, the agent must explore parts of the environment it does not know well, while at the same time exploiting its knowledge to maximize performance. RL thus provides a framework for learning to behave optimally in unknown environments, which has already been applied to robotics, game playing, network management and traffic control.
The goal of the IEEE Symposium on ADPRL is to provide an outlet and a forum for interaction between researchers and practitioners in ADP and RL, in which the clear parallels between the two fields are brought together and exploited. We equally welcome contributions from control theory, computer science, operations research, computational intelligence, neuroscience, as well as other novel perspectives on ADPRL. We host original papers on methods, analysis, applications, and overviews of ADPRL. We are interested in applications from engineering, artificial intelligence, economics, medicine, and other relevant fields.
Specific topics of interest include, but are not limited to:
- Convergence and performance analysis
- RL and ADP-based control
- Function approximation and value function representation
- Complexity issues in RL and ADP
- Policy gradient and actor-critic methods
- Direct policy search
- Planning and receding-horizon methods
- Monte-Carlo tree search and other Monte-Carlo methods
- Adaptive feature discovery
- Parsimoneous function representation
- Statistical learning and PAC bounds for RL
- Learning rules and architectures
- Bandit techniques for exploration
- Bayesian RL and exploration
- Finite-sample analysis
- Partially observable Markov decision processes
- Neuroscience and biologically inspired control
- ADP and RL for multiplayer games and multiagent systems
- Distributed intelligent systems
- Multi-objective optimization for ADPRL
- Transfer learning
- Applications of ADP and RL
Accepted papers will be published in the SSCI proceedings and on IEEEXplore, conditioned on registering and presenting the paper at the conference. See Important Dates and Practical Info, which includes the link to the submission site.
- A title, together with a mention that the proposal is for the ADPRL symposium.
- A brief description, rationale or motivation for the session.
- List of topics and scope.
- Importance and relevance to SSCI and ADPRL, possibly included in the description above.
- A tentative list of contributions, with the names of authors who have already been invited to participate.
- Short biosketches of the proposers.
Please submit your special session proposal to any of the ADPRL organizers before 1 May 2015. Proposals will be reviewed for quality and coherence with the conference topics, and the organizers will be notified of the decision.
Reinforcement Learning with the Internet of Things, Please click here to download the CFP for the special session. (Organiser: Ann Nowe, Vrije Universiteit Brussel, Belgium, Email: firstname.lastname@example.org, Yann-Michael De Hauwere, Vrije Universiteit Brussel, Belgium, Email: email@example.com, Joost Duflou, Katholieke Universiteit Leuven, Belgium, Email: firstname.lastname@example.org and Bruno Depraetere, Flanders Make, Belgium, Email: email@example.com ).
Vrije Universiteit Brussel, Belgium. E-mail: firstname.lastname@example.org
Dr. M.A. (Marco) Wiering|
University of Groningen, The Netherlands.
Technical University of Cluj-Napoca, Romania.
- Abhjit Gosavi, Missouri University of Science and Technology, USA
- Ann Nowe, Vrije Universiteit Brussel, Belgium
- Boris Defourny, Lehigh University, USA
- Danil Prokhorov, Toyota Technical Center, USA
- Dongbin Zhao, Chinese Academy of Sciences, China
- Draguna Vrabie, United Technologies Research Center, USA
- Eduardo Alonso, City University London, UK
- El-Sayed El Alfy, King Fahd University of Petroleum and Minerals, Saoudi Arabaia
- Girish Chowdhary, Oklahoma State University, USA
- Haibo He, University of Rhode Island, USA
- Hao Xu, Missouri University of Science and Technology, USA
- Huaguang Zhang, Northeastern University, China
- Jagannathan Sarangapani, Missouri University of Science and Technology, USA
- Janey Yu, Massachusetts Institute of Technology, USA
- Jennie Si, Arizona State University, USA
- Kang Li, Queen's University Belfast, UK
- Karl Tuyls, University of Liverpool, UK
- Kyriakos Vamvoudakis, University of California, Santa Barbara, USA
- Martijn van Otterlo, Radboud University Nijmegen, Netherlands
- Martin Riedmiller, University of Freiburg, Germany
- Matthieu Geist, Supelec Metz, France
- Philippe Preux, INRIA Lille Nord Europe, France
- Raphael Fonteneau, University of Liege, Belgium
- Remi Munos, INRIA Lille Nord Europe, France
- Shubhendu Bhasin, Indian Institute of Technology Delhi, India
- Somayeh Moazeni, Stevens Institute of Technology, USA
- Tobias Jung, University of Liege, Belgium
- Warren Powell, Princeton University, USA
- Xin Xu, National University of Defense Technology, China
- Yanhong Luo, Northeastern University, China
- Zeng-Guang Hou, Chinese Academy of Sciences, China