@InProceedings{parr97a,
  author =	 {Ronald Parr and Stuart Russell},
  title =	 {Reinforcement learning with hierarchies of machines},
  booktitle =	 {Proceedings of the 1997 conference on
                  Advances in neural information processing systems},
  year =	 1997,
  isbn =	 {0-262-10076-2},
  pages =	 {1043--1049},
  location =	 {Denver, Colorado, United States},
  publisher =	 {MIT Press},
  address =	 {Cambridge, MA, USA},
  abstract =	 {We present a new approach to reinforcement learning
                  in which the policies considered by the learning
                  process are constrained by hierarchies of partially
                  specified machines. This allows for the use of prior
                  knowledge to reduce the search space and provides a
                  framework in which knowledge can be transferred
                  across problems and in which component solutions can
                  be recombined to solve larger and more complicated
                  problems. Our approach can be seen as providing a
                  link between reinforcement learning and
                  ``behavior-based'' or ``teleo-reactive'' approaches
                  to control. We present provably convergent
                  algorithms for problem-solving and learning with
                  hierarchical machines and demonstrate their
                  effectiveness on a problem with several thousand
                  states.},
  keywords =     {learning reinforcement},
  googleid = 	 {OONdmqMSk-UJ:scholar.google.com/},
  url = 	 {http://jmvidal.cse.sc.edu/library/parr97a.pdf},
  cluster = 	 {16542586350140777272},
}