@article{Iqbal2026, 
author = {Adeel Iqbal and Tahir Khurshaid and Syed Abdul Mannan Kirmani and Mohammad Arif and Muhammad Faisal Siddiqui},
title = {ARQ–UCB: A Reinforcement-Learning Framework for Reliability-Aware and Efficient Spectrum Access in Vehicular IoT},
year = {2026},
journal = {Computers, Materials & Continua},
volume = {87},
number = {2},
pages = {65},
keywords = {V-IoT, RL, Q-Learning, upper confidence bound, spectrum access, URLLC, 5G/6G},
url = {https://www.sciopen.com/article/10.32604/cmc.2026.075819},
doi = {10.32604/cmc.2026.075819},
abstract = {Vehicular Internet of Things (V-IoT) networks need intelligent and adaptive spectrum access methods for ensuring ultra-reliable and low-latency communication (URLLC) in highly dynamic environments. Traditional reinforcement learning (RL)-based algorithms, such as Q-Learning and Double Q-Learning, are often characterized by unstable convergence and inefficient exploration in the presence of stochastic vehicular traffic and interference. This paper proposes Adaptive Reinforcement Q-learning with Upper Confidence Bound (ARQ-UCB), a lightweight and reliability-aware RL framework, which explicitly reduces interruption and blocking probabilities while improving throughput and delay across diverse vehicular traffic conditions. This proposed ARQ-UCB algorithm extends the basic Q-updates with an exploration confidence term able to dynamically balance exploration and exploitation based on uncertainty estimates, hence allowing faster convergence in case of bursty vehicular traffic. A comprehensive simulation framework evaluates throughput, delay, fairness, energy efficiency, and computational complexity in several V-IoT scenarios. Obtained results indicate that ARQ–UCB attains substantial gains in terms of throughput, fairness, and blocking/delay probabilities while retaining sub-20 μs decision latency and  𝒪(1) complexity per decision, thus validating real-time feasibility for reliable spectrum access in 5G and beyond V-IoT networks.}
}