A Caltech Library Service

Multi-dueling Bandits with Dependent Arms

Sui, Yanan and Zhuang, Vincent and Burdick, Joel W. and Yue, Yisong (2017) Multi-dueling Bandits with Dependent Arms. . (Unpublished)

[img] PDF - Submitted Version
See Usage Policy.


Use this Persistent URL to link to this item:


The dueling bandits problem is an online learning framework for learning from pairwise preference feedback, and is particularly well-suited for modeling settings that elicit subjective or implicit human feedback. In this paper, we study the problem of multi-dueling bandits with dependent arms, which extends the original dueling bandits setting by simultaneously dueling multiple arms as well as modeling dependencies between arms. These extensions capture key characteristics found in many real-world applications, and allow for the opportunity to develop significantly more efficient algorithms than were possible in the original setting. We propose the selfsparring algorithm, which reduces the multi-dueling bandits problem to a conventional bandit setting that can be solved using a stochastic bandit algorithm such as Thompson Sampling, and can naturally model dependencies using a Gaussian process prior. We present a no-regret analysis for multi-dueling setting, and demonstrate the effectiveness of our algorithm empirically on a wide range of simulation settings.

Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription Paper
Sui, Yanan0000-0002-9480-627X
Yue, Yisong0000-0001-9127-1989
Record Number:CaltechAUTHORS:20190410-120658254
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:94640
Deposited By: George Porter
Deposited On:10 Apr 2019 19:51
Last Modified:09 Mar 2020 13:19

Repository Staff Only: item control page