Dynamic Programming for Structured Continuous Markov Decision Problems
Abstract
We describe an approach for exploiting structure in Markov Decision Processes with continuous state variables. At each step of the dynamic programming, the state space is dynamically partitioned into regions where the value function is the same throughout the region. We first describe the algorithm for piecewise constant representations. We then extend it to piecewise linear representations, using techniques from POMDPs to represent and reason about linear surfaces efficiently. We show that for complex, structured problems, our approach exploits the natural structure so that optimal solutions can be computed efficiently.
Cite
Text
Feng et al. "Dynamic Programming for Structured Continuous Markov Decision Problems." Conference on Uncertainty in Artificial Intelligence, 2004.Markdown
[Feng et al. "Dynamic Programming for Structured Continuous Markov Decision Problems." Conference on Uncertainty in Artificial Intelligence, 2004.](https://mlanthology.org/uai/2004/feng2004uai-dynamic/)BibTeX
@inproceedings{feng2004uai-dynamic,
title = {{Dynamic Programming for Structured Continuous Markov Decision Problems}},
author = {Feng, Zhengzhu and Dearden, Richard and Meuleau, Nicolas and Washington, Richard},
booktitle = {Conference on Uncertainty in Artificial Intelligence},
year = {2004},
pages = {154-161},
url = {https://mlanthology.org/uai/2004/feng2004uai-dynamic/}
}