Browse > Article

A Dynamic Channel Assignment Method in Cellular Networks Using Reinforcement learning Method that Combines Supervised Knowledge  

Kim, Sung-Wan (서강대학교 컴퓨터공학과)
Chang, Hyeong-Soo (서강대학교 컴퓨터공학과)
Publication Information
Journal of KIISE:Computing Practices and Letters / v.14, no.5, 2008 , pp. 502-506 More about this Journal
Abstract
The recently proposed "Potential-based" reinforcement learning (RL) method made it possible to combine multiple learnings and expert advices as supervised knowledge within an RL framework. The effectiveness of the approach has been established by a theoretical convergence guarantee to an optimal policy. In this paper, the potential-based RL method is applied to a dynamic channel assignment (DCA) problem in a cellular networks. It is empirically shown that the potential-based RL assigns channels more efficiently than fixed channel assignment, Maxavail, and Q-learning-based DCA, and it converges to an optimal policy more rapidly than other RL algorithms, SARSA(0) and PRQ-learning.
Keywords
Reinforcement Learning; Cellular networks; Channel Assignment Methods; SARSA(0);
Citations & Related Records
연도 인용수 순위
  • Reference
1 Singh, S., Jaakkola, T., Littman, M. L., Szepesv'ari, C, "Convergence results for single-step on-policy reinforcement-learning algorithms," Journal of Machine Learning, Vol.38, No.3, pp. 287-308, 2000   DOI
2 R. Sutton and A. Barto, Reinforcement Learning. MIT Press, 2000
3 M. N. ahmadabadi and M. Asadpour, "Expertness based cooperative Q-learning," IEEE Trans. on Systems, Man, and Cybernetics, part B, Vol.32, No.1, pp. 66-76, 2002   DOI   ScienceOn
4 Junhong Nie; Haykin, S., "A dynamic channel assignment policy through Q-learning," IEEE Trans. on Neural Networks, Vol.10, No.6, pp. 1443-1455, 1999   DOI   ScienceOn
5 T. Mitchell, Machine Learning, McGraw Hill, 1989
6 Tekinay, S.; Jabbari, B., "Handover and channel assignment in mobile cellular networks," Communications Magazine, IEEE, Vol.29, No.11, pp. 42-46, 1991
7 A. Y. Ng, D. Harada, and S. Russel. "Policy invariance under reward transformations: theory and application to reward shaping," in Proc. of the 16th Int. Conf. on Machine Learning, pp. 278-287, 1999
8 M. L. Littman. Algorithms for sequential decision making. Unpublished Ph.D. Thesis, Brown University, Providence, R.I. 1996
9 H. S. Chang, "Reinforcement Learning with Supervision by Combining Multiple Learnings and Expert Advices," in Proc. of the 2006 American Control Conference, pp. 4159-4164, 2006