English

Thompson Sampling is Asymptotically Optimal in General Environments

Machine Learning 2016-06-06 v2 Artificial Intelligence Machine Learning

Abstract

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, non-ergodic, 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.

Keywords

Cite

@article{arxiv.1602.07905,
  title  = {Thompson Sampling is Asymptotically Optimal in General Environments},
  author = {Jan Leike and Tor Lattimore and Laurent Orseau and Marcus Hutter},
  journal= {arXiv preprint arXiv:1602.07905},
  year   = {2016}
}

Comments

UAI 2016

R2 v1 2026-06-22T12:57:40.808Z