ADP and Reinforcement Learning Technical Committee


Under the supervision and the coordination of the IEEE CIS Technical Activities Committee, The Adaptive Dynamic Programming and Reinforcement Learning Technical Committee (ADPRLTC) is established to promote the research, development, education, and understanding of adaptive dynamic programming and reinforcement learning methods, including both theoretical and experimental approaches.


ADPRLTC shall have a Chair, two Vice-Chairs and a number of Members. The Chair shall be appointed by the President of the Society in January. The ADPRLTC Chair shall appoint two Vice-Chairs and a number of Members. TC Chairs shall be appointed by the President of the Society in January. The TC Chair will then appoint two TC Vice-Chairs and TC Members. The appointment of the TC Vice-Chairs and the TC Members needs to be approved by the Vice President for Technical Activities. TC Chairs, Vice-Chairs and committee members must all be IEEE CIS members. The term of service expires at the end of the calendar year for which they have been appointed. If you are interested in being considered for a position on one of our Technical Committees, please send an email to with a link to your CV.

Committees Chairs and Members

Current directory of Chairs and members: Adaptive Dynamic Programming and Reinforcement Learning Technical Committee Members.


Funding for the committee shall be provided by the CIS in the annual budget request. Once approved by the CIS ExCom and AdCom, funds will be available to support the ADPRLTC activities. The Chair shall be responsible for the appropriate use of the approved funds with supporting documentation. 


The ADPRLTC shall engage in various activities in order to promote adaptive dynamic programming and reinforcement learning as a viable technology, including but not limited to the following: Identify and promote new areas of research, propose special sessions to the CIS-sponsored conference organizers, participate in paper review and selection for CIS-sponsored conferences and publications, coordinate with the International Neural Network Society for the International Joint Conference on Neural Networks in which ADPRL is also active, recommend candidates to different Award Committees such as for the best papers published in the Transactions on Neural Networks, promote IEEE Senior Members and Fellows program, collaborate on production of tutorials and book series, maintain the Committee¡¦s website, facilitate local chapters activities and organize specialized workshops or meetings. The ADPRLTC will assist in soliciting conference proposals and actively work with the organizers of CIS-sponsored conferences to insure their technical excellence.


Meetings will be called by the Chair once or twice a year, usually in conjunction with the CIS AdCom meetings and the World Congress on Computational Intelligence (WCCI) or the symposium series on computational intelligence (SSCI), or as requested by the ADPRLTC members. Sufficient advance notice of the meetings will be given to the members, as well as to other interested parties. The Chair shall prepare an agenda before the meeting, and shall prepare minutes for distribution after the meeting.


This Charter becomes official after at least 2/3 core members present at The Committee Meeting approves it. Subsequent changes and amendments also require 2/3 majority vote.

Task Forces

  • Applications of ADP and RL, Chair: Draguna Vrabie, Co-Chair: Zhong-Ping Jiang
  • ADP and RL in Real-Time Feedback Control Systems, Chair: Biao Luo, Vice-Chair: Xinglong Zhang
  • ADP in Game Theory and Multi-Agent Optimization, Chair: Kyriakos G. Vamvoudakis, Vice-Chair: Travis Dierks
  • Evolutionary Algorithms for ADPRL, Chair: Hisashi Handa, Vice-Chair: Kazuhiro Ohkura
  • Reinforcement Learning and Function Approximation, Chair: Robert Babuska, Vice-Chair: Damien Ernst
  • Reinforcement Learning for Robots, Chair: Adolfo Perrusquia, Vice-Chair: Zeng-Guang Hou
  • ADPRL TC Community, Chair: Zhuo Wang, Vice-Chair: Yuanheng Zhu
  • ADP and RL in Power and Energy Internets, Chair: Xiangjun Li, Vice Chair: Zhen Ni
  • AI and Edge Computing for Trustworthy Robots and Autonomous Systems: Chair: Dr Hongmei He, Vice chairs: Prof John Gray, Prof Martin Mcginnity, Prof Qinggang Meng, Prof Angelo Congelosi and Prof Jorn Mehnen.