Exploration Using Without-Replacement Sampling of Actions is Sometimes Inferior

Document Type

Presentation

Presentation Date

3-2021

Abstract or Description

Presentation given at the 100th Meeting of the Southeastern Section of the Mathematical Association of America.

Abstract

In many statistical and machine learning applications, without-replacement sampling is considered superior to with-replacement sampling. In some cases, this has been proven, and in others the heuristic is so intuitively attractive that it is taken for granted. In reinforcement learning, many count-based exploration strategies are justified by reliance on the aforementioned heuristic. This paper will detail the non-intuitive discovery that when measuring the goodness of an exploration strategy by the stochastic shortest path to a goal state, there is a class of processes for which an action selection strategy based on without-replacement sampling of actions can be worse than with replacement sampling. Specifically, the expected time until a specified goal state is first reached can be provably larger under without-replacement sampling. Numerical experiments describe the frequency and severity of this inferiority

Sponsorship/Conference/Institution

100th Meeting of the Southeastern Section of the Mathematical Association of America

Location

Virtual

Source

https://maasoutheastern.org/2021-conference/

This document is currently not available here.

Share

COinS