Reinforcement Learning Based Goodput Maximization with Quantized Feedback in URLLC

TL;DR

This paper develops a reinforcement learning-based method for optimizing feedback schemes to maximize goodput in URLLC systems with quantized channel information, adapting to changing channel conditions.

Contribution

It introduces a novel Rician-$K$ factor estimation technique and a reinforcement learning framework for dynamic feedback scheme optimization in URLLC.

Findings

Enhanced goodput performance in URLLC with quantized feedback.

Effective adaptation to varying channel statistics.

Improved system robustness through novel estimation technique.

Abstract

This paper presents a comprehensive system model for goodput maximization with quantized feedback in Ultra-Reliable Low-Latency Communication (URLLC), focusing on dynamic channel conditions and feedback schemes. The study investigates a communication system, where the receiver provides quantized channel state information to the transmitter. The system adapts its feedback scheme based on reinforcement learning, aiming to maximize goodput while accommodating varying channel statistics. We introduce a novel Rician-$K$ factor estimation technique to enable the communication system to optimize the feedback scheme. This dynamic approach increases the overall performance, making it well-suited for practical URLLC applications where channel statistics vary over time.