2012/07/11 by Zhengzhu Feng, Feng, Zhengzhu, Richard Dearden +5 · 1 citation
Computer Science · #Bayesian Modeling and Causal Inference #Formal Methods in Verification #Reinforcement Learning in Robotics #cs.AI
paper · pdf · doi:10.48550/arxiv.1207.4115
Appears in Proceedings of the Twentieth Conference on Uncertainty in Artificial Intelligence (UAI2004)
arxiv created 2012/07/11 · arxiv updated 2012/07/19
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.