Towards Exploiting Duality in Approximate Linear Programming for MDPs

@inproceedings{Dolgov2005TowardsED,
  title={Towards Exploiting Duality in Approximate Linear Programming for MDPs},
  author={Dmitri A. Dolgov and Edmund H. Durfee},
  booktitle={AAAI},
  year={2005}
}
A weakness of classical methods for solving Markov decision processes is that they scale very poorly because of the flat state space, which subjects them to the curse of dimensionality. Fortunately, many MDPs are well-structured, which makes it possible to avoid enumerating the state space. To this end, factored MDP representations have been proposed (Boutilier, Dearden, & Goldszmidt 1995; Koller & Parr 1999) that model the state space as a cross product of state features, represent the… CONTINUE READING
1 Citations
9 References
Similar Papers