Robust Control of Markov Decision Processes with Uncertain Transition Matrices

Download: .pdf

Authors: A. Nilim and L. El Ghaoui.

Status: Operations Research, Vol. 53, No. 5, September - October, 2005.

Abstract: Optimal solutions to Markov decision problems may be very sensitive with respect to the state transition probabilities. In many practical problems, the estimation of these probabilities is far from accurate. Hence, estimation errors are limiting factors in applying Markov decision processes to real-world problems. We consider a robust control problem for a finite-state, finite-action Markov decision process, where uncertainty on the transition matrices is described in terms of possibly nonconvex sets. We show that perfect duality holds for this problem, and that as a consequence, it can be solved with a variant of the classical dynamic programming algorithm, the ‘‘robust dynamic programming’’ algorithm. We show that a particular choice of the uncertainty sets, involving likelihood regions or entropy bounds, leads to both a statistically accurate representation of uncertainty, and a complexity of the robust recursion that is almost the same as that of the classical recursion. Hence, robustness can be added at practically no extra computing cost. We derive similar results for other uncertainty sets, including one with a finite number of possible values for the transition matrices. We describe in a practical path planning example the benefits of using a robust strategy instead of the classical optimal strategy; even if the uncertainty level is only crudely guessed, the robust strategy yields a much better worst-case expected travel time.

Related entries:

• A. Nilim, L. El Ghaoui. Robust Markov Decision processes. Workshop on Learning and Planning in Markov Processes – Advances and Challenges, American Association for Artificial Intelligence, San Jose, July 2004.

• A. Nilim and L. El Ghaoui. Robust Markov Decision Processes with Uncertain Transition Matrices. EECS Department Technical Report No. UCB/ERL M04/28, 2004.

• El Ghaoui, L. and A. Nilim, Robust Solutions to Markov Decision Problems with Uncertain Transition Matrices. Proc. NIPS, 2003.

• Nilim, A., L. El Ghaoui, and V. Duong, “Robust Dynamic Routing of Aircraft under uncertainty.” in IEEE 21st Digital Avionics Systems Conference, 2002.

Bibtex reference: