A Deep Actor-Critic Reinforcement Learning Framework for Dynamic Multichannel Access

TL;DR

This paper introduces a deep actor-critic reinforcement learning framework for dynamic multichannel access, effectively managing spectral resources in single and multi-user scenarios with adaptive capabilities and performance advantages over existing methods.

Contribution

It develops a novel deep actor-critic RL framework for both single and multi-user multichannel access, including algorithms and extensive evaluations in dynamic environments.

Findings

The framework outperforms DQN and random access in average reward and efficiency.

It adapts well to time-varying channel conditions.

Multi-user analysis shows reduced collision probabilities.

Abstract

To make efficient use of limited spectral resources, we in this work propose a deep actor-critic reinforcement learning based framework for dynamic multichannel access. We consider both a single-user case and a scenario in which multiple users attempt to access channels simultaneously. We employ the proposed framework as a single agent in the single-user case, and extend it to a decentralized multi-agent framework in the multi-user scenario. In both cases, we develop algorithms for the actor-critic deep reinforcement learning and evaluate the proposed learning policies via experiments and numerical results. In the single-user model, in order to evaluate the performance of the proposed channel access policy and the framework's tolerance against uncertainty, we explore different channel switching patterns and different switching probabilities. In the case of multiple users, we analyze the probabilities of each user accessing channels with favorable channel conditions and the probability of collision. We also address a time-varying environment to identify the adaptive ability of the proposed framework. Additionally, we provide comparisons (in terms of both the average reward and time efficiency) between the proposed actor-critic deep reinforcement learning framework, Deep-Q network (DQN) based approach, random access, and the optimal policy when the channel dynamics are known.