Introduction to multi-agent Modified Q-learning Routing for computer networks

Proceedings - Advanced Industrial Conference on Telecommunications/Service Assurance with Partial and Intermittent Resources Conference/E-Learning on Telecommunications Workshop AICT/SAPIR/ELETE 2005

Volumn 2005, Issue , 2005, Pages 408-415

  Rudek, Radoslaw ^a   Koszałka, Leszek ^a   Pozniak Koszałka, Iwona ^a  

^a WROCLAW UNIVERSITY OF TECHNOLOGY   (Poland)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTER NETWORKS; DISTRIBUTED COMPUTER SYSTEMS; LEARNING ALGORITHMS; MULTI AGENT SYSTEMS; TELECOMMUNICATION NETWORKS;

DETERMINISTIC ROUTING; DISTRIBUTED SYSTEMS; Q-LEARNING ROUTING; REINFORCEMENT LEARNING;

ROUTERS;

EID: 33751011337     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/AICT.2005.53     Document Type: Conference Paper

References (17)

1. S. P. M. Choi, D. Y. Yeung. Predictive Q-Routing: A memory-based reinforcement learning approach to adaptive traffic control, Advances in Neural Information Processing Systems, 8:945-951, Editors: Touretzky D. S., Mozer M. C., Hasselmo M. E., MIT Press, Cambridge, 1996.
2. W. J. Dally. Virtual channel flow control. IEEE Transactions on Parallel and Distributed Systems, 3:194-205, 1992.
3. W. J. Dally, C. L. Seitz. The torus routing chip. Journal of Distributed Computing, 1:187-196, 1986.
4. A. Kasprzak. Packet switching wide area networks. Oficyna Wydawnicza Politechniki Wrocławskiej, Wrocław, 1997 (In Polish).
5. L. P. Kaebling, M. L. Littman, A. W. Moore. Reinforcement learning: a survey. Journal of Artificial Intelligence Research, 4:237-285, 1996.
6. P. Kermani, L. Kleinrock. Virtual Cut-Through: A new computer communication switching technique. Computer Networks, 3:267-286, 1979.
7. S. Koenig, R. Simmons. Complexity analysis of real-time reinforcement learning applied to finding shortest path in deterministic domains. Machine Learning: A Special Issue on Reinforcement Learning, 12: 234-345, 1997.
8. T. Mitchell. Machine learning, McGraw-Hill International Editions, 1997.
9. A. W. Najjar, A. Lagman, S. Sur, P. K. Srimani. Analytical model of adaptive routing strategies. Technical Report CS-94-105, Colorado State University, 1994.
10. R. Rudek. Q-Learning based algorithms for solving unknown structure multi-criteria graphs. Proc. of the IIIth Polish Conference on Computer Pattern Recognition Systems KOSYR, Miłków, 2003, pp. 190-195 (In Polish).
11. R. Rudek. Experimentation system for evaluating and analysis of adaptive routing algorithms. M.Sc. Thesis, Wroclaw University of Technology, Wrocław, 2004 (In Polish).
12. P. Stone, M. Veloso. Multiagent systems: a survey from a machine learning perspective. Autonomous Robots, 8:345-383, 2000.
13. R. Sutton, A. Barto. Reinforcement learning, MIT Press, Cambridge, 1998.
14. M. Tan. Multi-agent reinforcement learning: Independent vs. cooperative learning, Morgan Kaufmann, 1997.
15. A. S. Tanenbaum. Computer network, Prentice-Hall, 1988.
16. J. Upadhyay, V. Varavithya, P. Mohapatra. A traffic-balanced adaptive wormhole-routing scheme for two-dimensional meshes. IEEE Transactions on Computers, 2:190-197, 1997.
17. C. Watkins, P. Dayan. Q-learning. Machine Learning 8:279-292, 1992.