pith. sign in

arxiv: 2007.05456 · v1 · pith:FUI2FKBTnew · submitted 2020-07-10 · 💻 cs.LG · stat.ML

Improved Analysis of UCRL2 with Empirical Bernstein Inequality

Ronan Fruit , Matteo Pirotta , Alessandro Lazaric This is my paper
classification 💻 cs.LG stat.ML
keywords analysisbernsteinempiricalgammastatesucrl2ucrl2bactions
0
0 comments X
read the original abstract

We consider the problem of exploration-exploitation in communicating Markov Decision Processes. We provide an analysis of UCRL2 with Empirical Bernstein inequalities (UCRL2B). For any MDP with $S$ states, $A$ actions, $\Gamma \leq S$ next states and diameter $D$, the regret of UCRL2B is bounded as $\widetilde{O}(\sqrt{D\Gamma S A T})$.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Sample Complexity Bounds for Stochastic Shortest Path with a Generative Model

    cs.LG 2026-04 unverdicted novelty 7.0

    SSP requires Omega(S A B_star^3 / (c_min epsilon^2)) samples in the worst case, with matching upper bounds that hold even for c_min=0 under bounded optimal hitting time.