Wireless MAC Protocol Synthesis and Optimization With Multi-Agent Distributed Reinforcement Learning

IEEE Networking Letters, vol. 6, pp. 242–246

Abstract

In this letter, we propose a novel Multi-Agent Deep Reinforcement Learning (MADRL) framework for MAC protocol design. Unlike centralized approaches, which rely on a single entity for decision-making, MADRL empowers individual network nodes to autonomously learn and optimize their MAC from local observations. Our framework is the first of a kind that enables distributed multi-agent learning within the ns-3 environment, and facilitates the design and synthesis of adaptive MAC protocols tailored to specific environmental conditions. We demonstrate the effectiveness of the MADRL framework through extensive simulations, showcasing superior performance compared to legacy protocols across diverse scenarios.

Authors 3

1. Navid Keshtiarast Aachen Mobile Communications and Computing Group

   RWTH Aachen University

   Affiliation as printed

   Mobile Communications and Computing Group, RWTH Aachen University, Aachen, Germany

   Mobile Communications and Computing Group, RWTH Aachen University, Germany

2. Oliver Renaldi Aachen Mobile Communications and Computing Group

   RWTH Aachen University

   Affiliation as printed

   Mobile Communications and Computing Group, RWTH Aachen University, Aachen, Germany

   Mobile Communications and Computing Group, RWTH Aachen University, Germany

3. Marina Petrova Aachen Mobile Communications and Computing Group

   RWTH Aachen University

   Affiliation as printed

   Mobile Communications and Computing Group, RWTH Aachen University, Aachen, Germany

   Mobile Communications and Computing Group, RWTH Aachen University, Germany