Efficient spectrum sharing is essential for maximizing data communication performance in Vehicular Networks (VNs). In this article, we propose a novel hybrid framework that leverages Multi-Agent Reinforcement Learning (MARL), thereby combining both centralized and decentralized learning approaches. This framework addresses scenarios where multiple vehicle-to-vehicle (V2V) links reuse the frequency spectrum preoccupied by vehicle-to-infrastructure (V2I) links. We introduce the QMIX technique with the Deep Q Networks (DQNs) algorithm to facilitate collaborative learning and efficient spectrum management. The DQN technique uses a neural network to approximate the Q value function in high-dimensional state spaces, thus mapping input states to (action, Q value) tables that facilitate self-learning across diverse scenarios. Similarly, the QMIX is a value-based technique for multi-agent environments. In the proposed model, each V2V agent having its own DQN observes the environment, receives observation, and obtains a common reward. The QMIX network receives Q values from all agents considering individual benefits and collective objectives. This mechanism leads to collective learning while V2V agents dynamically adapt to real-time conditions, thus improving VNs performance. Our research finding highlights the potential of hybrid MARL models for dynamic spectrum sharing in VNs and paves the way for advanced cooperative learning strategies in vehicular communication environments. Furthermore, we conducted an in-depth exploration of the simulation environment and performance evaluation criteria, thus concluding in a comprehensive comparative analysis with cutting-edge solutions in the field. Simulation results show that the proposed framework efficiently performs against the benchmark architecture in terms of V2V transmission probability and V2I peak data transfer.

Multiple Input Multiple Output (MIMO) systems have been gaining significant attention from the research community due to their potential to improve data rates. However, a suitable scheduling mechanism is required to efficiently distribute available spectrum resources and enhance system capacity. This paper investigates the user selection problem in Multi-User MIMO (MU-MIMO) environment using the multi-agent Reinforcement learning (RL) methodology. Adopting multiple antennas’ spatial degrees of freedom, devices can serve to transmit simultaneously in every time slot. We aim to develop an optimal scheduling policy by optimally selecting a group of users to be scheduled for transmission, given the channel condition and resource blocks at the beginning of each time slot. We first formulate the MU-MIMO scheduling problem as a single-state Markov Decision Process (MDP). We achieve the optimal policy by solving the formulated MDP problem using RL. We use aggregated sum-rate of the group of users selected for transmission, and a $20\%$ higher sum-rate performance over the conventional methods is reported.