This paper focuses on spectrum sharing in heterogeneous wireless networks, where nodes with different Media Access Control (MAC) protocols to transmit data packets to a common access point over a shared wireless channel. While previous studies have proposed Deep Reinforcement Learning (DRL)-based multiple access protocols tailored to specific scenarios, these approaches are limited by their inability to generalize across diverse environments, often requiring time-consuming retraining. To address this issue, we introduce Generalizable Multiple Access (GMA), a novel Meta-Reinforcement Learning (meta-RL)-based MAC protocol designed for rapid adaptation across heterogeneous network environments. GMA leverages a context-based meta-RL approach with Mixture of Experts (MoE) to improve representation learning, enhancing latent information extraction. By learning a meta-policy during training, GMA enables fast adaptation to different and previously unknown environments, without prior knowledge of the specific MAC protocols in use. Simulation results demonstrate that, although the GMA protocol experiences a slight performance drop compared to baseline methods in training environments, it achieves faster convergence and higher performance in new, unseen environments.

Reinforcement learning has been widely used to train a sequential power control policy from simulation environment in Internet of Vehicles. However, disturbance is usually inevitably introduced when the agent getting into the practical environment from the simulation environment, which leads to a critical challenge when multiple links share a common spectrum. This paper is dedicated to addressing this issue in a two-pronged way. On one hand, we set the aim of policy learning as minimizing the network transmission outage probability from a risk-sensitive perspective. On the other hand, we propose a meta soft actor-critic based power control scheme, where the key hyperparameter is auto-adjusted to adapt to environment variations and L2 regulation is taken in the loss function of critic network to avoid overfitting to the simulation environment. Simulation results show that, the proposed algorithm achieves a higher successful transmission probability under the same conditions and is more robust under disturbed environment, than the baseline schemes.

This paper focuses on spectrum sharing in heterogenous wireless networks, where different nodes utilize various Media Access Control (MAC) protocols to transmit data packets to a common access point on a shared wireless channel. Previous studies have developed Deep Reinforcement Learning (DRL) based multiple access protocols for specific scenarios within heterogeneous wireless networks. However, there exists a wide range of coexisting scenarios, characterized by varying numbers of nodes and the use of different MAC protocols. Existing approaches require training new models from scratch when encountering unseen scenarios, resulting in significant training time. To address this issue, we propose a novel MAC protocol called Generalized Multiple Access (GMA), which employs the Meta-Reinforcement Learning (meta-RL) algorithm. By learning a meta-policy during training, GMA enable the fast adaptation of the agent node to different and previously unknown heterogeneous network environments, without prior knowledge of the specific MAC protocols used in those environments. We conduct a performance comparison between the proposed GMA protocol and existing DRL-based protocols. Simulation results demonstrate that while the GMA protocol experiences a slight performance loss compared to baseline methods in training environments, it demonstrates faster convergence and higher performance in new environments compared to baseline methods.