Abstract
This paper proposes a multi-agent deep reinforcement learning-based buffer-aided relay selection scheme for an intelligent reflecting surface (IRS)-assisted secure cooperative network in the presence of an eavesdropper. We consider a practical phase model where both phase shift and reflection amplitude are discrete variables to vary the reflection coefficients of the IRS. Furthermore, we introduce the buffer-aided relay to enhance the secrecy performance, but the use of the buffer leads to the cost of delay. Thus, we aim to maximize either the average secrecy rate with a delay constraint or the throughput with both delay and secrecy constraints, by jointly optimizing the buffer-aided relay selection and the IRS reflection coefficients. To obtain the solution of these two optimization problems, we divide each of the problems into two sub-tasks and then develop a distributed multi-agent reinforcement learning scheme for the two cooperative sub-tasks, each relay node represents an agent in the distributed learning. We apply the distributed reinforcement learning scheme to optimize the IRS reflection coefficients, and then utilize an agent on the source to learn the optimal relay selection based on the optimal IRS reflection coefficients in each iteration. Simulation results show that the proposed learning-based scheme uses an iterative approach to learn from the environment for approximating an optimal solution via the exploration of multiple agents, which outperforms the benchmark schemes.