Thompson Sampling is Asymptotically Optimal in General Environments. (arXiv:1602.07905v2 [cs.LG] UPDATED)

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.

from cs.AI updates on arXiv.org http://ift.tt/24sga6v
via IFTTT