Multi-Objective Reinforcement Learning for Cognitive Radar Resource Management
This work contributes to more efficient and adaptive cognitive radar systems for balancing competing objectives in dynamic environments, but it is incremental as it applies existing methods to a specific domain.
The paper tackled the time allocation problem in multi-function cognitive radar systems by formulating it as a multi-objective optimization and using deep reinforcement learning, with SAC showing improved stability and sample efficiency over DDPG.
The time allocation problem in multi-function cognitive radar systems focuses on the trade-off between scanning for newly emerging targets and tracking the previously detected targets. We formulate this as a multi-objective optimization problem and employ deep reinforcement learning to find Pareto-optimal solutions and compare deep deterministic policy gradient (DDPG) and soft actor-critic (SAC) algorithms. Our results demonstrate the effectiveness of both algorithms in adapting to various scenarios, with SAC showing improved stability and sample efficiency compared to DDPG. We further employ the NSGA-II algorithm to estimate an upper bound on the Pareto front of the considered problem. This work contributes to the development of more efficient and adaptive cognitive radar systems capable of balancing multiple competing objectives in dynamic environments.