Saved in:
Bibliographic Details
Main Authors: Li, Peizheng, Lin, Xinyi, Aijaz, Adnan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.15640
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917278008737792
author Li, Peizheng
Lin, Xinyi
Aijaz, Adnan
author_facet Li, Peizheng
Lin, Xinyi
Aijaz, Adnan
contents Semantic communication promises task-aligned transmission but must reconcile semantic fidelity with stringent latency guarantees in immersive and safety-critical services. This paper introduces a time-constrained human-in-the-loop reinforcement learning (TC-HITL-RL) framework that embeds human feedback, semantic utility, and latency control within a semantic-aware Open radio access network (RAN) architecture. We formulate semantic adaptation driven by human feedback as a constrained Markov decision process (CMDP) whose state captures semantic quality, human preferences, queue slack, and channel dynamics, and solve it via a primal--dual proximal policy optimization algorithm with action shielding and latency-aware reward shaping. The resulting policy preserves PPO-level semantic rewards while tightening the variability of both air-interface and near-real-time RAN intelligent controller processing budgets. Simulations over point-to-multipoint links with heterogeneous deadlines show that TC-HITL-RL consistently meets per-user timing constraints, outperforms baseline schedulers in reward, and stabilizes resource consumption, providing a practical blueprint for latency-aware semantic adaptation.
format Preprint
id arxiv_https___arxiv_org_abs_2602_15640
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Latency-aware Human-in-the-Loop Reinforcement Learning for Semantic Communications
Li, Peizheng
Lin, Xinyi
Aijaz, Adnan
Signal Processing
Machine Learning
Semantic communication promises task-aligned transmission but must reconcile semantic fidelity with stringent latency guarantees in immersive and safety-critical services. This paper introduces a time-constrained human-in-the-loop reinforcement learning (TC-HITL-RL) framework that embeds human feedback, semantic utility, and latency control within a semantic-aware Open radio access network (RAN) architecture. We formulate semantic adaptation driven by human feedback as a constrained Markov decision process (CMDP) whose state captures semantic quality, human preferences, queue slack, and channel dynamics, and solve it via a primal--dual proximal policy optimization algorithm with action shielding and latency-aware reward shaping. The resulting policy preserves PPO-level semantic rewards while tightening the variability of both air-interface and near-real-time RAN intelligent controller processing budgets. Simulations over point-to-multipoint links with heterogeneous deadlines show that TC-HITL-RL consistently meets per-user timing constraints, outperforms baseline schedulers in reward, and stabilizes resource consumption, providing a practical blueprint for latency-aware semantic adaptation.
title Latency-aware Human-in-the-Loop Reinforcement Learning for Semantic Communications
topic Signal Processing
Machine Learning
url https://arxiv.org/abs/2602.15640