pith. sign in

arxiv: 1505.01918 · v3 · pith:2VWRUUBTnew · submitted 2015-05-08 · 📊 stat.ML · cs.LG

An Asymptotically Optimal Policy for Uniform Bandits of Unknown Support

classification 📊 stat.ML cs.LG
keywords ldotspolicyregretasymptoticallycontrollerfiniteoptimalpopulations
0
0 comments X
read the original abstract

Consider the problem of a controller sampling sequentially from a finite number of $N \geq 2$ populations, specified by random variables $X^i_k$, $ i = 1,\ldots , N,$ and $k = 1, 2, \ldots$; where $X^i_k$ denotes the outcome from population $i$ the $k^{th}$ time it is sampled. It is assumed that for each fixed $i$, $\{ X^i_k \}_{k \geq 1}$ is a sequence of i.i.d. uniform random variables over some interval $[a_i, b_i]$, with the support (i.e., $a_i, b_i$) unknown to the controller. The objective is to have a policy $\pi$ for deciding, based on available data, from which of the $N$ populations to sample from at any time $n=1,2,\ldots$ so as to maximize the expected sum of outcomes of $n$ samples or equivalently to minimize the regret due to lack on information of the parameters $\{ a_i \}$ and $\{ b_i \}$. In this paper, we present a simple inflated sample mean (ISM) type policy that is asymptotically optimal in the sense of its regret achieving the asymptotic lower bound of Burnetas and Katehakis (1996). Additionally, finite horizon regret bounds are given.

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.