StreamingBandit : Experimenting with Bandit Policies

Show full item record



Permalink

http://hdl.handle.net/10138/324462

Citation

Kruijswijk , J , van Emden , R , Parvinen , P & Kaptein , M 2020 , ' StreamingBandit : Experimenting with Bandit Policies ' , Journal of Statistical Software , vol. 94 , no. 9 , pp. 1-47 . https://doi.org/10.18637/jss.v094.i09

Title: StreamingBandit : Experimenting with Bandit Policies
Author: Kruijswijk, Jules; van Emden, Robin; Parvinen, Petri; Kaptein, Maurits
Contributor: University of Helsinki, Department of Economics and Management
Date: 2020-08
Language: eng
Number of pages: 47
Belongs to series: Journal of Statistical Software
ISSN: 1548-7660
URI: http://hdl.handle.net/10138/324462
Abstract: A large number of statistical decision problems in the social sciences and beyond can be framed as a (contextual) multi-armed bandit problem. However, it is notoriously hard to develop and evaluate policies that tackle these types of problems, and to use such policies in applied studies. To address this issue, this paper introduces StreamingBandit, a Python web application for developing and testing bandit policies in field studies. StreamingBandit can sequentially select treatments using (online) policies in real time. Once StreamingBandit is implemented in an applied context, different policies can be tested, altered, nested, and compared. StreamingBandit makes it easy to apply a multitude of bandit policies for sequential allocation in field experiments, and allows for the quick development and re-use of novel policies. In this article, we detail the implementation logic of StreamingBandit and provide several examples of its use.
Subject: sequential decision-making
multi-armed bandit
data streams
sequential experimentation
Python
CLINICAL-TRIALS
112 Statistics and probability
Rights:


Files in this item

Total number of downloads: Loading...

Files Size Format View
v94i09.pdf 1013.Kb PDF View/Open

This item appears in the following Collection(s)

Show full item record