Reinforcement Learning for Routing Strategy Considering the State of Network Link

Abstract:

This paper presents reinforcement learning (RL) algorithm for routing strategy considering the state of network link, which can be deemed as a dynamic programming problem with stochastic needs. Through modeling those four elements and experiments, we draw the conclusion that upon the state of network link, RL is an efficient algorithm for routing strategy; the data can be efficient forwarded to the destination.

• Periodical: Applied Mechanics and Materials (Volumes 220-223)
• Pages: 2772-2776
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.220-223.2772
• Online since: November 2012
• Authors: Zhao Hui Hu
• Keywords: Epsilon Greedy, Network Link Status, Reinforcement Learning, Routing Strategy

References

[1] C. Lochert, H Hartenstein, J Tian, etc, "A routing strategy for vehicular ad hoc networks in city environments" Proceedings of the 2003 IEEE International Conference on intelligent Vehicles Symposium, 2003, pp, 156-161.

DOI: 10.1109/ivs.2003.1212901

[2] G. Malkin, "Rip version 2: carrying additional information", http://etherpad.tools.ietf.org/html/rfc1723

[3] K. Kompella, Ed. and Y. Rekhter, Ed. ,"OSPF Extensions in Support of Generalized Multi-Protocol Label witching (GMPLS)", http://trac.tools.ietf.org/html/rfc4203

DOI: 10.17487/rfc4203

[4] R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction. Massachusetts London, England: The MIT Press Cambridge, 1998.

[5] Wen Shang and Dong Sun, "Distributed neural network-based policy gradient reinforcement learning for multi-robot formations", Proceedings of the 2008 IEEE International Conference on Information and Automation, pp.113-118.

DOI: 10.1109/icinfa.2008.4607978

[6] L. Peshkin and V.Savova , "Reinforcement learning for adaptive routing", International Joint Conference on Neural Networks (IJCNN), 2002, pp, 1825-1830

DOI: 10.1109/ijcnn.2002.1007796

[7] JA. Boyan and ML. Littman, "Packet routing in dynamically changing networks: a reinforcement learning approach", In Advances in Neural Information Processing Systems, 1994, pp, 671-678.

[8] Z. H. Hu, D. B. Zhao, "Reinforcement learning for multi-agent patrol policy," IEEE International Conference on Cognitive Informatics, 2010, pp.530-535

DOI: 10.1109/coginf.2010.5599681

[9] C. Watkins, "Q-learning," Machine Learning, 1992, vol. 8, no.3, pp.279-292.

[10] A. G. Barto, T. G. Dietterich, "Reinforcement learning and its relationship to supervised learning," in J. Si, A. Barto, W. Powell, and D. Wunsch. Handbook of Learning and Approximate Dynamic Programming, IEEE Press, John Wiley & sons, Inc., 2004, pp.47-63.

DOI: 10.1109/9780470544785

[11] D. B. Zhao, Z. Zhang, Y. J. Dai. "Self-teaching adaptive dynamic programming for Go-Moku," Neurocomputing, vol.78, 2012, pp.23-29.

DOI: 10.1016/j.neucom.2011.05.032