A distributed reinforcement learning scheme for network routing
| Author(s) : | Justin Boyan Michael Littman, |
| Publisher : | N/A |
| Publication Date : | 1993 |
| ISSN : | N/A |
| Abstract : | 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., |