Resource allocation of distributed MIMO radar based on the hybrid action space reinforcement learning

The distributed multiple-input multiple-output (MIMO) radar system exhibits superior target localization capability by jointly processing target information from multiple radars under different observation angles. To improve the resource utilization of the distributed MIMO radar system, this paper proposes a hybrid action space reinforcement learning (HAS-RL) method, aiming to maximize the target localization performance under the radar resource constraints. Specifically, the Cramer–Rao Lower Bound (CRLB) incorporating the transmit radar power and receive radar selection is first derived and employed as the target localization performance metric of the distributed MIMO radar system. Subsequently, the radar resource allocation problem is modeled as a constrained optimization problem with continuous and discrete variables, and a hybrid action space reinforcement learning is proposed to solve the above optimization problem. Simulation results demonstrate that the proposed HAS-RL method can obtain better target localization performance under the given radar resource constraints.