The Emergence of Wireless MAC Protocols with Multi-Agent Reinforcement Learning
This addresses the challenge of automated protocol design in wireless networks, offering an incremental improvement over existing methods.
The paper tackles the problem of designing wireless MAC protocols by proposing a multi-agent reinforcement learning framework using MADDPG, where base stations and user equipment learn to cooperate without prior signaling agreements, achieving superior goodput compared to a contention-free baseline.
In this paper, we propose a new framework, exploiting the multi-agent deep deterministic policy gradient (MADDPG) algorithm, to enable a base station (BS) and user equipment (UE) to come up with a medium access control (MAC) protocol in a multiple access scenario. In this framework, the BS and UEs are reinforcement learning (RL) agents that need to learn to cooperate in order to deliver data. The network nodes can exchange control messages to collaborate and deliver data across the network, but without any prior agreement on the meaning of the control messages. In such a framework, the agents have to learn not only the channel access policy, but also the signaling policy. The collaboration between agents is shown to be important, by comparing the proposed algorithm to ablated versions where either the communication between agents or the central critic is removed. The comparison with a contention-free baseline shows that our framework achieves a superior performance in terms of goodput and can effectively be used to learn a new protocol.