Expert Selection in High-Dimensional Markov Decision Processes

10/26/2020
by   Vicenc Rubies Royo, et al.
8

In this work we present a multi-armed bandit framework for online expert selection in Markov decision processes and demonstrate its use in high-dimensional settings. Our method takes a set of candidate expert policies and switches between them to rapidly identify the best performing expert using a variant of the classical upper confidence bound algorithm, thus ensuring low regret in the overall performance of the system. This is useful in applications where several expert policies may be available, and one needs to be selected at run-time for the underlying environment.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset