@COMMENT This file was generated by bib2html.pl <http://www.cs.cmu.edu/~pfr/misc_software/index.html#bib2html> version 0.91
@COMMENT written by Patrick Riley <http://www.cs.cmu.edu/~pfr>
@COMMENT This file came from Jefferson Provosts's publication pages at
@COMMENT http://www.cnbc.cmu.edu/~jp/research/publications
@TechReport{provost-ai-tr-05-319,
  author = 	 {Jefferson Provost and Benjamin J. Kuipers and Risto Miikkulainen},
  title = 	 {Self-Organizing Distinctive State Abstraction for Learning Robot Navigation},
  institution =  {The University of Texas at Austin, Department of Computer Sciences},
  year = 	 2005,
  number =	 {AI-TR-05-319},
  address =	 {Austin, Texas},
  month =	 {July},
  abstract = {A major challenge in reinforcement learning research is to extend methods that have worked well on discrete, short-range, low-dimensional problems to continuous, high-diameter, high-dimensional problems, such as robot navigation using high-resolution sensors. Self-Organizing Distinctive-state Abstraction (SODA) is a new, generic method by which a robot in a continuous world can better learn to navigate by learning a set of high-level features and building temporallyextended actions to carry it between distinctive states based on those features. A SODA agent first uses a self-organizing feature map to develop a set of high-level perceptual features while exploring the environment with primitive, local actions. The agent then builds a set of high-level actions composed of generic trajectory-following and hill-climbing control laws that carry it between the states at local maxima of feature activations. In an experiment on a simulated robot navigation task, the SODA agent learns to perform a task requiring 300 small-scale, local actions using as few as 9 new, temporallyextended actions, significantly improving learning time over navigating with the local actions.
}
}