Dynamic Programming for Structured Continuous Markov Decision Problems
Zhengzhu Feng, Richard Dearden, Nicolas Meuleau, Richard Washington
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.
PDF Link: /papers/04/p154-feng.pdf
AUTHOR = "Zhengzhu Feng
and Richard Dearden and Nicolas Meuleau and Richard Washington",
TITLE = "Dynamic Programming for Structured Continuous Markov Decision Problems",
BOOKTITLE = "Proceedings of the Twentieth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-04)",
PUBLISHER = "AUAI Press",
ADDRESS = "Arlington, Virginia",
YEAR = "2004",
PAGES = "154--161"