Sciweavers

Share
UAI
2004

Dynamic Programming for Structured Continuous Markov Decision Problems

8 years 10 months ago
Dynamic Programming for Structured Continuous Markov Decision Problems
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.
Zhengzhu Feng, Richard Dearden, Nicolas Meuleau, R
Added 31 Oct 2010
Updated 31 Oct 2010
Type Conference
Year 2004
Where UAI
Authors Zhengzhu Feng, Richard Dearden, Nicolas Meuleau, Richard Washington
Comments (0)
books