An adaptive network routing strategy with temporal differences Reportar como inadecuado




An adaptive network routing strategy with temporal differences - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

Marley M. Vellasco ; Marco A. Pacheco ;Inteligencia Artificial. Revista Iberoamericana de Inteligencia Artificial 2001, 5 (12)

Autor: Yván Túpac Valdivia

Fuente: http://www.redalyc.org/


Introducción



Inteligencia Artificial.
Revista Iberoamericana de Inteligencia Artificial ISSN: 1137-3601 revista@aepia.org Asociación Española para la Inteligencia Artificial España Túpac Valdivia, Yván; Vellasco, Marley M.; Pacheco, Marco A. An adaptive network routing strategy with temporal differences Inteligencia Artificial.
Revista Iberoamericana de Inteligencia Artificial, vol.
5, núm.
12, primavera, 2001, pp.
85-91 Asociación Española para la Inteligencia Artificial Valencia, España Available in: http:--www.redalyc.org-articulo.oa?id=92551211 How to cite Complete issue More information about this article Journals homepage in redalyc.org Scientific Information System Network of Scientific Journals from Latin America, the Caribbean, Spain and Portugal Non-profit academic project, developed under the open access initiative An Adaptive Network Routing Strategy with Temporal Differences Yván Túpac Valdivia, Marley M.
Vellasco, Marco A.
Pacheco ICA: Applied Computational Intelligence Laboratory Pontifícia Universidade Católica do Rio de Janeiro Rio de Janeiro - BRAZIL {yvantv, marley, marco}@ele.puc-rio.br Abstract This paper describes the TD-Routing, an adaptive algorithm for packet routing, based on the Temporal Differences TD(λ) method, and compares its performance with other routing strategies: Shortest Path Routing, Bellman-Ford and the Q-Routing.
High and low network traffic conditions are considered.
In contrast with other algorithms that are also based on Reinforcement Learning (RL), the TD-Routing is able to discover good policies for situations that present a reduction in network traffic.
The performance of the proposed algorithm was evaluated within a benchmark network configuration of 16 nodes with different traffic conditions in different topologies.
The simulations demonstrate that the TD-Routing outperforms other RL-based algorithms in terms of learning speed and adaptability. Keywords: Reinforcement Learning, Packet Routing, Network Communica...





Documentos relacionados