Policy-Gradient Algorithms for Partially Observable Markov Decision Processes. Aberdeen, D. Ph.D. Thesis, Australian National University, 2003.
bibtex   
@PhDThesis{aberdeenthesis,
  author = {D. Aberdeen},
  year = {2003},
  title={Policy-Gradient Algorithms for
  Partially Observable Markov Decision Processes},
  school = {Australian National University} }

Downloads: 0