The Community for Technology Leaders
Hybrid Intelligent Systems, International Conference on (2005)
Rio de Janeiro, Brazil
Dec. 6, 2005 to Dec. 9, 2005
ISBN: 0-7695-2457-5
pp: 251-258
Manoel Junior Leandro de Lima , Universidade Federal do Rio Grande do Norte, Campus Universitario, Natal, Brazil
Jorge Dantas de Melo , Universidade Federal do Rio Grande do Norte, Campus Universitario, Natal, Brazil
Adriao Duarte Doria Neto , Universidade Federal do Rio Grande do Norte, Campus Universitario, Natal, Brazil
ABSTRACT
The use of reinforcement learning to implement Metrical Task Systems is limited to smaller scale problems due to the curse of dimensionality inherent in the method. This paper aims to present an algorithm based on decomposition techniques which allows us to apply this approach to realistic control problems. It analyzes aspects associated with the quality of the solution and its limitations, as well as discuss about the relevant theoretical topics of the approach presented.
INDEX TERMS
null
CITATION

A. D. Doria Neto, M. . Leandro de Lima and J. Dantas de Melo, "Hierarchical Reinforcement Learning for Metrical Task Systems," Hybrid Intelligent Systems, International Conference on(HIS), Rio de Janeiro, Brazil, 2005, pp. 251-258.
doi:10.1109/ICHIS.2005.55
96 ms
(Ver 3.3 (11022016))