A Distributed Reinforcement Learning Scheme for Network Routing

  title={A Distributed Reinforcement Learning Scheme for Network Routing},
  author={Michael L. Littman and Justin A. Boyan},
In this paper we describe a self-adjusting algorithm for packet routing, in which a reinforcement learning module is embedded into each node of a switching network. Only local communication is used to keep accurate statistics at each node on which routing policies lead to minimal delivery times. In simple experiments involving a 36-node, irregularly connected network, this learning approach proves superior to a nonadaptive algorithm based on precomputed shortest paths. The authors would like to… CONTINUE READING
Highly Cited
This paper has 142 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 87 extracted citations

143 Citations

Citations per Year
Semantic Scholar estimates that this publication has 143 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-6 of 6 references

Reinforcement Learning for Robots Using Neural Networks

  • L.-J. Lin
  • PhD thesis,
  • 1993
1 Excerpt

Practial issues in temporal di erence learning

  • G. Tesauro
  • Machine Learning,
  • 1992
1 Excerpt

On routing and delta routing: A taxonomy and performance comparison of techniques for packet-switched networks

  • H. Rudin
  • IEEE Transac- tions on Communications,
  • 1976
1 Excerpt

Flows in Networks

  • L. R. Ford, Jr.
  • 1962
1 Excerpt

On a routing problem

  • R. Bellman
  • Quarterly of Applied Mathematics,
  • 1958
1 Excerpt

Similar Papers

Loading similar papers…