Robustness in Markov Decision Problems with Uncertain Transition Matrices

  title={Robustness in Markov Decision Problems with Uncertain Transition Matrices},
  author={Arnab Nilim and Laurent El Ghaoui},
Optimal solutions to Markov Decision Problems (MDPs) are very sensitive with respect to the state transition probabilities. In many practical problems, the estimation of those probabilities is far from accurate. Hence, estimation errors are limiting factors in applying MDPs to realworld problems. We propose an algorithm for solving finite-state and finite-action MDPs, where the solution is guaranteed to be robust with respect to estimation errors on the state transition probabilities. Our… CONTINUE READING
Highly Cited
This paper has 48 citations. REVIEW CITATIONS


Publications referenced by this paper.

Decision Processes: Discrete Stochastic Dynamic Programming

  • M. Putterman.Markov
  • 1994
1 Excerpt

Prior distributions on space of probability measures

  • T. Ferguson
  • The Annal of Statistics,
  • 1974
1 Excerpt

Kleywegt . Minimax analysis of stochastic problems

  • J. A.
  • OptimizationMethods and Software
  • 1973

Similar Papers

Loading similar papers…