Thompson Sampling Is Asymptotically Optimal in General Environments

Jan Leike et al

We discuss a variant of Thompson sampling for nonparametric reinforcement learning in a countable classes of general stochastic environments.

These environments can be non-Markov, nonergodic, and partially observable. We show that Thompson sampling learns the environment class in the sense that (1) asymptotically its value converges to the optimal value in mean and (2) given a recoverability assumption regret is sublinear.

Powered by Hexo and Hexo-theme-hiker

Copyright © 2013 - 2017 Universality All Rights Reserved.

UV : | PV :