Networked Restless Multi-Arm Bandits with Reinforcement Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Hanmo, Sun, Zenghui, Wang, Kai
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914183056982016
author Zhang, Hanmo
Sun, Zenghui
Wang, Kai
author_facet Zhang, Hanmo
Sun, Zenghui
Wang, Kai
contents Restless Multi-Armed Bandits (RMABs) are a powerful framework for sequential decision-making, widely applied in resource allocation and intervention optimization challenges in public health. However, traditional RMABs assume independence among arms, limiting their ability to account for interactions between individuals that can be common and significant in a real-world environment. This paper introduces Networked RMAB, a novel framework that integrates the RMAB model with the independent cascade model to capture interactions between arms in networked environments. We define the Bellman equation for networked RMAB and present its computational challenge due to exponentially large action and state spaces. To resolve the computational challenge, we establish the submodularity of Bellman equation and apply the hill-climbing algorithm to achieve a $1-\frac{1}{e}$ approximation guarantee in Bellman updates. Lastly, we prove that the approximate Bellman updates are guaranteed to converge by a modified contraction analysis. We experimentally verify these results by developing an efficient Q-learning algorithm tailored to the networked setting. Experimental results on real-world graph data demonstrate that our Q-learning approach outperforms both $k$-step look-ahead and network-blind approaches, highlighting the importance of capturing and leveraging network effects where they exist.
format Preprint
id arxiv_https___arxiv_org_abs_2512_06274
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Networked Restless Multi-Arm Bandits with Reinforcement Learning
Zhang, Hanmo
Sun, Zenghui
Wang, Kai
Machine Learning
Artificial Intelligence
Restless Multi-Armed Bandits (RMABs) are a powerful framework for sequential decision-making, widely applied in resource allocation and intervention optimization challenges in public health. However, traditional RMABs assume independence among arms, limiting their ability to account for interactions between individuals that can be common and significant in a real-world environment. This paper introduces Networked RMAB, a novel framework that integrates the RMAB model with the independent cascade model to capture interactions between arms in networked environments. We define the Bellman equation for networked RMAB and present its computational challenge due to exponentially large action and state spaces. To resolve the computational challenge, we establish the submodularity of Bellman equation and apply the hill-climbing algorithm to achieve a $1-\frac{1}{e}$ approximation guarantee in Bellman updates. Lastly, we prove that the approximate Bellman updates are guaranteed to converge by a modified contraction analysis. We experimentally verify these results by developing an efficient Q-learning algorithm tailored to the networked setting. Experimental results on real-world graph data demonstrate that our Q-learning approach outperforms both $k$-step look-ahead and network-blind approaches, highlighting the importance of capturing and leveraging network effects where they exist.
title Networked Restless Multi-Arm Bandits with Reinforcement Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2512.06274