Confidence Based Dual Reinforcement Q-Routing: An adaptive online network routing algorithm

  title={Confidence Based Dual Reinforcement Q-Routing: An adaptive online network routing algorithm},
  author={Shailesh Kumar and Risto Miikkulainen},
This paper describes and evaluates the Con dence-based Dual Reinforcement QRouting algorithm (CDRQ-Routing) for adaptive packet routing in communication networks. CDRQ-Routing is based on an application of the Q-learning framework to network routing, as rst proposed by Littman and Boyan (1993). The main contribution of CDRQ-routing is an increased quantity and an improved quality of exploration. Compared to Q-Routing, the state-of-the-art adaptive Bellman-Ford Routing algorithm, and the non… CONTINUE READING
Highly Cited
This paper has 54 citations. REVIEW CITATIONS


Publications citing this paper.

54 Citations

Citations per Year
Semantic Scholar estimates that this publication has 54 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 11 references

Con dence based dual reinforcement q-routing: An on-line adaptive network routing algorithm

Shailesh Kumar
Master's thesis, Department of Computer Sciences, The University of Texas at Austin, Austin, TX78712, USA, • 1998
View 4 Excerpts

In Machine Learning: Proceedings of the 13th Annual Conference (Bari

Patrick Goetz, Shailesh Kumar, Risto Miikkulainen. On-line adaptation of a signal predi learning
Italy), • 1996
View 3 Excerpts

Numerical Recipies in C

W. H. Press, S. A. Teukolsky, W. T. Vellering, B. P. Flannery
Cambridge University Press, Cambridge, UK • 1995
View 1 Excerpt

pages 45{51

M. Littman, J. A. Boyan. A distributed reinforcement learning sch Telecommunications
Hillside, New Jersy, • 1993
View 2 Excerpts


C.J.C.H. Watkins, P. Dayan
Machine Learning, 8:279{292 • 1989
View 1 Excerpt

Dynamic programming.

Science • 1966
View 2 Excerpts

Similar Papers

Loading similar papers…