Reinforcement-routing information page

This page gives pointers to several papers concerning the use of reinforcement-learning techniques to solve problems in network routing.

Papers

Justin A. Boyan and Michael L. Littman. Packet routing in dynamically changing networks: A reinforcement learning approach. In Jack D. Cowan, Gerald Tesauro, and Joshua Alspector, editors, Advances in Neural Information Processing Systems, volume 6, pages 671--678. Morgan Kaufmann, San Francisco CA, 1993. (abstract, postscript)

Michael L. Littman and Justin A. Boyan. A distributed reinforcement learning scheme for network routing. In Joshua Alspector, Rodney Goodman, and Timothy X. Brown, editors, Proceedings of the 1993 International Workshop on Applications of Neural Networks to Telecommunications, pages 45--51. Lawrence Erlbaum Associates, Hillsdale NJ, 1993. (abstract, postscript)

Michael Littman and Justin Boyan. A distributed reinforcement learning scheme for network routing. Technical Report CMU-CS-93-16, School of Computer Science, Carnegie Mellon University, Pittsburgh PA, July, 1993. (abstract, postscript)

John W. Bates. Packet routing and reinforcement learning: Estimating shortest paths in dynamic graphs. Unpublished manuscript, 1995. (postscript)

Samuel P.M. Choi and Dit-Yan Yeung. Predictive Q-routing: A memory-based reinforcement learning approach to adaptive traffic control. To appear in Advances in Neural Information Processing Systems 8, D. S. Touretzky, M. C. Mozer, M. E. Hasselmo, eds., MIT Press, 1996. In press. (abstract, compressed postscript)

Shailesh Kumar and Risto Miikkulainen. Dual Reinforcement Q-Routing: An On-line adaptive routing algorithm. In C. H. Dagli, M. Akay, O. Ersoy, B. R. Fernandez and A. Smith (editors), Smart Engineering Systems: Neural Networks, Fuzzy Logic, Data Mining, and Evolutionary Programming: Volume 7 in Intelligent Engineering Systems Through Artificial Neural Networks (ANNIE-97, St. Louis, MO), 231-238. New York: ASME Press, 1997. ( paper page)

Kumar, S. 1998. Confidence Based Dual Reinforcement Q-routing. Master's thesis, Dept. of Comp. Sci, The University of Texas at Austin.

Devika Subramanian, Peter Druschel, and Johnny Chen. Ants and reinforcement learning: A case study in routing in dynamic networks, In Proceedings of IJCAI-97, 1997. (citeseer)

Ann Nowe has also done some work on Q routing, which was presented at CONALD in Pittsburgh, June 1998. Other papers, pointed out by Ted Perkins:

A Multi-Agent, Policy-Gradient approach to Network Routing (ICML 2001)
Nigel Tao, Jonathan Baxter, Lex Weaver

TPOT-RL Applied to Network Routing (ICML 2000)
Peter Stone

Dual reinforcement q-routing: An on-line adaptive routing algorithm. (Proc. of the Artificial Neural Networks in Engineering Conference, 1997)
S. Kumar, R. Muukkulainen

Confidence-based dual reinforcement q-routing: an on-line adaptive network routing algorithm. (Master's thesis, UT-Austin)
S. Kumar

Predictive Q-routing: A memory-based reinforcement learning approach to adaptive traffic control. (NIPS 1995?) Choi, Yeung.

Ants and reinforcement learning: A case study in routing in dynamic networks. (IJCAI 1997) Devika Subramanian, Peter Druschel, and Johnny Chen.

Bob Givan has worked on a number of network-related problems, I believe with some RL-related approaches.

Other links

For more information, contact Michael Littman: mlittman@cs.duke.edu. Last update: Thu Jul 18 07:35:39 EDT 1996