CORE: Compensable Reward as a Catalyst for Improving Offline RL in Wireless Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zu, Lipeng, Zhou, Hansong, Qian, Yu, Chakraborty, Shayok, Yuan, Yukun, Guo, Linke, Zhang, Xiaonan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915691334991872
author Zu, Lipeng
Zhou, Hansong
Qian, Yu
Chakraborty, Shayok
Yuan, Yukun
Guo, Linke
Zhang, Xiaonan
author_facet Zu, Lipeng
Zhou, Hansong
Qian, Yu
Chakraborty, Shayok
Yuan, Yukun
Guo, Linke
Zhang, Xiaonan
contents Real-world wireless data are expensive to collect and often lack sufficient expert demonstrations, causing existing offline RL methods to overfit suboptimal behaviors and exhibit unstable performance. To address this issue, we propose CORE, an offline RL framework specifically designed for wireless environments. CORE identifies latent expert trajectories from noisy datasets via behavior embedding clustering, and trains a conditional variational autoencoder with a contrastive objective to separate expert and non-expert behaviors in latent space. Based on the learned representations, CORE constructs compensable rewards that reflect expert-likelihood, effectively guiding policy learning under limited or imperfect supervision. More broadly, this work represents one of the early systematic explorations of offline RL in wireless networking, where prior adoption remains limited. Beyond introducing offline RL techniques to this domain, we further examine intrinsic wireless data characteristics and develop a domain-aligned algorithm that explicitly accounts for their structural properties. While offline RL has not yet been fully established as a standard methodology in the wireless community, our study aims to provide foundational insights and empirical evidence to support its broader acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2512_19671
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CORE: Compensable Reward as a Catalyst for Improving Offline RL in Wireless Networks
Zu, Lipeng
Zhou, Hansong
Qian, Yu
Chakraborty, Shayok
Yuan, Yukun
Guo, Linke
Zhang, Xiaonan
Networking and Internet Architecture
Real-world wireless data are expensive to collect and often lack sufficient expert demonstrations, causing existing offline RL methods to overfit suboptimal behaviors and exhibit unstable performance. To address this issue, we propose CORE, an offline RL framework specifically designed for wireless environments. CORE identifies latent expert trajectories from noisy datasets via behavior embedding clustering, and trains a conditional variational autoencoder with a contrastive objective to separate expert and non-expert behaviors in latent space. Based on the learned representations, CORE constructs compensable rewards that reflect expert-likelihood, effectively guiding policy learning under limited or imperfect supervision. More broadly, this work represents one of the early systematic explorations of offline RL in wireless networking, where prior adoption remains limited. Beyond introducing offline RL techniques to this domain, we further examine intrinsic wireless data characteristics and develop a domain-aligned algorithm that explicitly accounts for their structural properties. While offline RL has not yet been fully established as a standard methodology in the wireless community, our study aims to provide foundational insights and empirical evidence to support its broader acceptance.
title CORE: Compensable Reward as a Catalyst for Improving Offline RL in Wireless Networks
topic Networking and Internet Architecture
url https://arxiv.org/abs/2512.19671