Linear Program Approximations for Factored Continuous-State Markov Decision Processes

Abstract

Approximate linear programming (ALP) has emerged recently as one of the most promising methods for solving complex factored MDPs with (cid:2)nite state spaces. In this work we show that ALP solutions are not limited only to MDPs with (cid:2)nite state spaces, but that they can also be applied successfully to factored continuous-state MDPs (CMDPs). We show how one can build an ALP-based approximation for such a model and contrast it to existing solution methods. We argue that this approach offers a robust alternative for solving high dimensional continuous-state space problems. The point is supported by experiments on three CMDP problems with 24-25 continuous state factors.

Cite

Text

Hauskrecht and Kveton. "Linear Program Approximations for Factored Continuous-State Markov Decision Processes." Neural Information Processing Systems, 2003.

Markdown

[Hauskrecht and Kveton. "Linear Program Approximations for Factored Continuous-State Markov Decision Processes." Neural Information Processing Systems, 2003.](https://mlanthology.org/neurips/2003/hauskrecht2003neurips-linear/)

BibTeX

@inproceedings{hauskrecht2003neurips-linear,
  title     = {{Linear Program Approximations for Factored Continuous-State Markov Decision Processes}},
  author    = {Hauskrecht, Milos and Kveton, Branislav},
  booktitle = {Neural Information Processing Systems},
  year      = {2003},
  pages     = {895-902},
  url       = {https://mlanthology.org/neurips/2003/hauskrecht2003neurips-linear/}
}