A Distributed Reinforcement Learning Scheme for Network Routing
Abstract
In this paper we describe a self-adjusting algorithm for packet routing, ill 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.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jul 01, 1993
- Accession Number
- ADA270600
Entities
People
- Justin Boyan
- Michael L. Littman
Organizations
- Carnegie Mellon University