Browse > Article

On-line Reinforcement Learning for Cart-pole Balancing Problem  

Kim, Byung-Chun (한경대학교 웹정보공학과)
Lee, Chang-Hoon (한경대학교 컴퓨터공학과)
Publication Information
The Journal of the Institute of Internet, Broadcasting and Communication / v.10, no.4, 2010 , pp. 157-162 More about this Journal
Abstract
The cart-pole balancing problem is a pseudo-standard benchmark problem from the field of control methods including genetic algorithms, artificial neural networks, and reinforcement learning. In this paper, we propose a novel approach by using online reinforcement learning(OREL) to solve this cart-pole balancing problem. The objective is to analyze the learning method of the OREL learning system in the cart-pole balancing problem. Through experiment, we can see that approximate faster the optimal value-function than Q-learning.
Keywords
Reinforcement Learning; Q-learning; Cart-pole Balaning; Optimal value function;
Citations & Related Records
연도 인용수 순위
  • Reference
1 김병천, 윤병주, "복수전략학습", 정보과학회지, 13권, 5호, pp45-52, 1995.
2 M.L.Minsky Theory of Neural-Analog Reinforcement Systems and Application to the Brain-Model Problem, Ph.D. Thesis, Princeton University, Princeton, 1954.
3 A. G. Barto, D. A. White and D. A. Sofge, "Reinforcement Learning and adaptive critic model", Handbook of Intelligent Control, pp. 469-491,1992.
4 C. W. Anderson, "Learning to control an inverted pendulum using neural networks", IEEE Control Systems Magazine, pp.31-37, 1989.
5 O. Pinngern and T. H. Nguyen, "International Symposium on Electrical & Electronics Engineering", HCM City, Vietnam, 2007.
6 As'ad Salkham, Raymond Cunningham, Anurag Garg, and Vinny Cahill, "A Collaborative Reinforcement Learning Approach to Urban Traffic Control", IEEE/WIC/ACM International Conference, Vol. 2 (2008), pp. 560-566.
7 T. Walczak and P. Cichosz. "A distributed learning control system for elevator groups", Artificial Intelligence and Soft Computing (ICAISC-06), volume 4029 of Lecture Notes in Computer Science, pp.1223–232. Springer, 2006.
8 K Conn and R A Peters, ""Reinforcement Learning with a Supervisor for a Mobile Robot in a Real world Environment", Computational Intelligence in Robotics and Automation, pp. 73-78, 2007
9 G. Cybenko, R. Gray, and K. Moizumi, "Q-learning : A Tutorial and Extensions", Mathematics of Artificial Neural Networks, Oxford University, July, 1995.