Solving Uncertain Markov Decision Problems

August 2001

Solving Uncertain Markov Decision Problems

Authors:

J. Andrew (Drew) Bagnell, Andrew Y. Ng, and Jeff Schneider
Technical Report
CMU-RI-TR-01-25

Abstract:

The authors consider the fundamental problem of finding good policies in uncertain models. It is demonstrated that although the general problem of finding the best policy with respect to the worst model is NP-hard, in the special case of a convex uncertainty set the problem is tractable. A stochastic dynamic game is proposed, and the security equilibrium solution of the game is shown to correspond to the value function under the worst model and the optimal controller. The authors demonstrate that the uncertain model approach can be used to solve a class of emph{nearly} Markovian Decision Problems, providing lower bounds on performance in stochastic models with higher-order interactions. The framework considered establishes connections between and generalizes paradigms of stochastic optimal, mini-max, and $H_infty$/robust control. Applications are considered, including robustness in reinforcement learning, planning in nearly Markovian decision processes, and bounding error due to sensor discretization in noisy, continuous state-spaces.
@techreport{Bagnell-2001-8291,
author = {J. Andrew (Drew) Bagnell And Andrew Y. Ng And Jeff Schneider},
title = {Solving Uncertain Markov Decision Problems},
year = {2001},
month = {August},
institute = {Carnegie Mellon University},
address = {Pittsburgh, PA},
number = {CMU-RI-TR-01-25},
keywords = {Uncertainty, MDPs, robust control, stochastic optimal control, dynamic programming, reinforcement learning, risk sensitive control},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.