Scalable Joint Learning of Wireless Multiple-Access Policies and their Signaling

TL;DR

This paper introduces a multi-agent reinforcement learning framework for jointly optimizing wireless multiple-access policies and signaling, demonstrating improved performance and scalability in high traffic scenarios.

Contribution

It presents the first scalable MARL approach for joint learning of access policies and signaling in wireless networks, outperforming traditional baselines.

Findings

Achieves higher goodput compared to baselines.

Maintains low collision rates even under high traffic.

Provides initial results on scalability in MARL for wireless access.

Abstract

In this paper, we apply an multi-agent reinforcement learning (MARL) framework allowing the base station (BS) and the user equipments (UEs) to jointly learn a channel access policy and its signaling in a wireless multiple access scenario. In this framework, the BS and UEs are reinforcement learning (RL) agents that need to cooperate in order to deliver data. The comparison with a contention-free and a contention-based baselines shows that our framework achieves a superior performance in terms of goodput even in high traffic situations while maintaining a low collision rate. The scalability of the proposed method is studied, since it is a major problem in MARL and this paper provides the first results in order to address it.