Liangrong Yi, Raphael Finkel, Judy Goldsmith
We are interested in building decision-support software for social welfare case managers. Our model in the form of a factored Markov decision process is so complex that a standard factored MDP solver was unable to solve it efficiently. We discuss factors contributing to the complexity of the model, then present a receding horizon planner that offers a rough policy quickly. Our planner computes locally, both in the sense of only offering one action suggestion at a time (rather than a complete policy) and because it starts from an initial state and considers only states reachable from there in its calculations.
Subjects: 3. Automated Reasoning; 3.4 Probabilistic Reasoning
Submitted: Feb 25, 2008