Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
1142159 | Operations Research Letters | 2014 | 4 Pages |
Abstract
An optimal strategy in a Markov decision problem is robust if it is optimal in every decision problem (not necessarily stationary) that is close to the original problem. We prove that when the state and action spaces are finite, an optimal strategy is robust if and only if it is the unique optimal strategy.
Related Topics
Physical Sciences and Engineering
Mathematics
Discrete Mathematics and Combinatorics
Authors
Gal Oren, Eilon Solan,