Multi-agent learning for routing control within an Internet environment

Engineering Applications of Artificial Intelligence

Volumn 17, Issue 2, 2004, Pages 179-185

  Tillotson, P R J ^a   Wu, Q H ^a   Hughes, P M ^b  

^a UNIVERSITY OF LIVERPOOL   (United Kingdom)

^b MARTLESHAM HEATH   (United Kingdom)

Author keywords

Internet control; Multi agent learning

Indexed keywords

COMPUTER NETWORKS; COMPUTER SIMULATION; CONTROL SYSTEMS; INTERNET; LEARNING SYSTEMS; PARALLEL PROCESSING SYSTEMS; ROUTERS; VIRTUAL REALITY;

CONTROL ROUTING; INTERNET CONTROL; MULTI-AGENT LEARNING; Q-LEARNING ALGORITHMS;

MULTI AGENT SYSTEMS;

EID: 2042544751     PISSN: 09521976     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.engappai.2004.02.004     Document Type: Article

References (10)

1. Anderson, C.W., 1989. Learning to control an inverted pendulum using neural networks. IEEE Control Systems Magazine (4), 31-37.
2. Boutilier, C., Dean, T., Hanks, S., 1995. Planning under uncertainty: structural assumptions and computational leverage. In: Proceedings of the Second European Workshop on Planning.
3. Comer D. Internetworking with TCP/IP. 1995;Prentice-Hall, Englewood Cliffs, NJ.
4. Hedrick, C., 1998. Routing information protocol. Http://www.ietf.org/rfc/ rfc1058.txt.
5. Kaelbling, L.P.K., Littman, M.L., Moore, A.W., 1996. Reinforcement learning: a survey. Journal of Artificial Intelligence (4), 237.
6. Sutton, R.S., 1992. Introduction: the challenge of reinforcement learning. Machine Learning (8), 228.
7. Watkins, C., Dayan, P., 1992. Technical note: Q-learning. Machine Learning (8), 279.
8. White D. Markov Decision Processes. 1993;Wiley, New York.
9. Wright, G.R., Stevens, W.R., 1995. TCP/IP Illustrated, Vol. 2. Addison-Wesley, Reading, MA.
10. Wu, Q.H., 1995. Reinforcement learning control using interconnected learning automata. International Journal of Control (62), 1.