Thumbnail
Access Restriction
Open

Author Littman, Michael ♦ Boyan, Justin
Source CiteSeerX
Content type Text
Publisher Erlbaum
File Format PDF
Language English
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword Packet Routing ♦ Simple Experiment ♦ Local Communication ♦ Self-adjusting Algorithm ♦ Accurate Statistic ♦ Minimal Delivery Time ♦ Distributed Reinforcement ♦ Network Routing ♦ Reinforcement Learning Module ♦ Precomputed Shortest Path ♦ Nonadaptive Algorithm
Description In this paper we describe a self-adjusting algorithm for packet routing, in which a reinforcement learning module is embedded into each nodeofa 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.
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study
Learning Resource Type Article
Publisher Date 1993-01-01
Publisher Institution In Proceedings of the 1993 International Workshop on Applications of Neural Networks to Telecommunications