Optimizing Vehicular Networks with Variational Quantum Circuits-based Reinforcement Learning

TL;DR

This paper introduces a novel variational quantum circuit-based multi-objective reinforcement learning framework to improve decision-making in vehicular networks, achieving faster convergence and higher rewards than traditional methods.

Contribution

The paper presents the first application of variational quantum circuits in multi-objective reinforcement learning for vehicular networks, enhancing policy efficiency and convergence.

Findings

Faster convergence rates compared to deep-Q networks

Higher reward optimization in vehicular network tasks

Effective multi-objective decision-making in VNet scenarios

Abstract

In vehicular networks (VNets), ensuring both road safety and dependable network connectivity is of utmost importance. Achieving this necessitates the creation of resilient and efficient decision-making policies that prioritize multiple objectives. In this paper, we develop a Variational Quantum Circuit (VQC)-based multi-objective reinforcement learning (MORL) framework to characterize efficient network selection and autonomous driving policies in a vehicular network (VNet). Numerical results showcase notable enhancements in both convergence rates and rewards when compared to conventional deep-Q networks (DQNs), validating the efficacy of the VQC-MORL solution.