Flexible Decomposition Algorithms for Weakly Coupled Markov Decision Problems
This addresses scalability issues in stochastic decision-making for researchers and practitioners in AI and operations research, though it appears incremental as it builds on existing decomposition techniques.
The paper tackles large Markov decision problems by introducing two decomposition algorithms, a partial decoupling method and a complete decoupling method, which divide problems into smaller pieces and achieve optimal or approximately optimal policies with provable bounds.
This paper presents two new approaches to decomposing and solving large Markov decision problems (MDPs), a partial decoupling method and a complete decoupling method. In these approaches, a large, stochastic decision problem is divided into smaller pieces. The first approach builds a cache of policies for each part of the problem independently, and then combines the pieces in a separate, light-weight step. A second approach also divides the problem into smaller pieces, but information is communicated between the different problem pieces, allowing intelligent decisions to be made about which piece requires the most attention. Both approaches can be used to find optimal policies or approximately optimal policies with provable bounds. These algorithms also provide a framework for the efficient transfer of knowledge across problems that share similar structure.