Reinforcement Q-learning for optimal tracking control of linear discrete-time systems with unknown dynamics. Kiumarsi, B., Lewis, F. L., Modares, H., Karimpour, A., & Naghibi-Sistani, M. Automatica, 50(4):1167–1175, April, 2014.
bibtex   
@Article{SCC.Kiumarsi.Lewis.ea2014,
  author    = {Kiumarsi, Bahare and Lewis, Frank L. and Modares, Hamidreza and Karimpour, Ali and Naghibi-Sistani, Mohammad-Bagher},
  title     = {Reinforcement {Q}-learning for optimal tracking control of linear discrete-time systems with unknown dynamics},
  journal   = {Automatica},
  year      = {2014},
  volume    = {50},
  number    = {4},
  pages     = {1167--1175},
  month     = apr,
  timestamp = {2015-01-01},
}

Downloads: 0