Dynamic Channel Access Via Meta-reinforcement Learning

Abstract

In this paper, we address the channel access problem in a dynamic wireless environment via meta-reinforcement learning. Spectrum is a scarce resource in wireless communications, especially with the dramatic increase in the number of devices in networks. Recently, inspired by the success of deep reinforcement learning (DRL), extensive studies have been conducted in addressing wireless resource allocation problems via DRL. However, training DRL algorithms usually requires a massive amount of data collected from the environment for each specific task and the well-trained model may fail if there is a small variation in the environment. In this work, in order to address these challenges, we propose a meta-DRL framework that incorporates the method of Model-Agnostic Meta-Learning (MAML). In the proposed framework, we train a common initialization for similar channel selection tasks. From the initialization, we show that only a few gradient descents are required for adapting to different task

Stats

• citations5
• S2 citations—
• github stars0
• HF likes0
• heat score5.84
• arxiv keylu2021dynamic

Related papers

• Meta-reinforcement Learning For Fast And Data-efficient Spectrum Allocation In Dynamic Wireless Networks (2025)0.00
• A Deep Actor-critic Reinforcement Learning Framework For Dynamic Multichannel Access (2019)15.22
• Dynamic Spectrum Access For Ambient Backscatter Communication-assisted D2D Systems With Quantum Reinforcement Learning (2024)0.00
• Resource Management In Wireless Networks Via Multi-agent Deep Reinforcement Learning (2020)16.43
• Deep Reinforcement Learning For Distributed Uncoordinated Cognitive Radios Resource Allocation (2019)0.00
• MDDL: A Framework For Reinforcement Learning-based Position Allocation In Multi-channel Feed (2023)2.26
• Deep Reinforcement Learning For Distributed And Uncoordinated Cognitive Radios Resource Allocation (2022)0.00
• Multi-agent Adversarial Attacks For Multi-channel Communications (2022)2.26