Vrettos Moulos

collaborators

Showing math.STShow all

3 papers · 1 filter

math.ST2020

Finite-Time Analysis of Round-Robin Kullback-Leibler Upper Confidence Bounds for Optimal Adaptive Allocation with Multiple Plays and Markovian Rewards

Vrettos Moulos

We study an extension of the classic stochastic multi-armed bandit problem which involves multiple plays and Markovian rewards in the rested bandits setting. In order to tackle thi…

math.ST2020

A Hoeffding Inequality for Finite State Markov Chains and its Applications to Markovian Bandits

Vrettos Moulos

This paper develops a Hoeffding inequality for the partial sums $\sum_{k = 1}^{n} f (X_{k})$ , where ${X_{k}}_{k \in Z_{> 0}}$ is an irreducible Markov chain on a finite state sp…

math.ST2019

Optimal Best Markovian Arm Identification with Fixed Confidence

Vrettos Moulos

We give a complete characterization of the sampling complexity of best Markovian arm identification in one-parameter Markovian bandit models. We derive instance specific nonasympto…