@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
@InProceedings{Provost-aaai04-ws9,
  author = 	 {Jefferson Provost and Benjamin J Kuipers and Risto Miikkulainen},
  title = 	 {Self-Organizing Perceptual and Temporal Abstraction for Robot Reinforcement Learning},
  booktitle = 	 {AAAI-04 Workshop on Learning and Planning in Markov Processes},
  year = 	 2004,
  abstract = { A major current challenge in reinforcement learning
research is to extend methods that work well on discrete, short-range,
low-dimensional problems to continuous, highdiameter, high-dimensional
problems, such as robot navigation using high-resolution sensors. We
present a method whereby an robot in a continuous world can, with
little prior knowledge of its sensorimotor system, environment, and
task, improve task learning by first using a self-organizing feature
map to develop a set of higher-level perceptual features while
exploring using primitive, local actions. Then using those features,
the agent can build a set of high-level actions that carry it between
perceptually distinctive states in the environment.  This method
combines a perceptual abstraction of the agent's sensory input
into useful perceptual features, and a temporal abstraction of the
agent's motor output into extended, high-level actions, thus
reducing both the dimensionality and the diameter of the task. An
experiment on a simulated robot navigation task shows that the agent
using this method can learn to perform a task requiring 300
small-scale, local actions using as few as 7 temporally-extended,
abstract actions, significantly improving learning time.},  
}