An Electronic Countermeasures Methodology Based on Monte Carlo Tree Search and Self-Play

Electronic countermeasures (ECM) can undermine radar target tracking capabilities through techniques such as suppression and deception, thereby enhancing the battlefield survivability of aircraft. This area has become a focal point of research within the field of electronic warfare. Emerging intelligent ECM methods leverage sophisticated jamming strategies and dynamic task allocation to fully exploit their potential against advanced radar target tracking systems. This paper introduces an effectiveness evaluation method from the perspective of the jammer, based on Monte Carlo Tree Search (MCTS) and self-play. By integrating MCTS with deep neural networks, the proposed method efficiently explores and evaluates countermeasure effectiveness within large state spaces. We conducted simulation experiments on a developed ECM simulation platform, assessing the algorithm's performance using real-world data. The simulation results validate our conclusion that the proposed approach outperforms other existing solutions in the literature.