Defensive and offensive capabilities are both significant in communication confrontation games. By exploiting the above two capabilities, a new confrontation mechanism in the spectrum domain between two opposing teams denoted as the blue team (BT) and red team (RT), is designed. The basic idea is that by sacrificing parts of ally performance to severely deteriorate the opponent side communications. Specifically, a friendly and smart jammer (assuming in the BT) is deployed to weaken opponent (i.e., members in the RT) communications without causing great damages to other BT members, while the smart RT members try to evade the jamming and alleviate mutual interference. The interactions among the friendly jammer and other nodes are modeled as a Stackelberg game, with each player seeking for their respective utility maximization. We prove that each sub-game is an exact potential game. To efficiently search for the equilibrium solutions, a parallel log-linear learning algorithm is proposed, based on which each user intelligently decides their spectrum access policies. Numerical results demonstrate that: 1) RT communications are effectively suppressed; meanwhile, mutual interference among ally BT communication pairs is significantly alleviated; 2) the proposed algorithm achieves a close-to-optimal solution; 3) compared with the current state of solutions, i.e., random selection, stochastic learning automata, our algorithm performs better in terms of both utility and convergence.

中文翻译：

---

基于学习的频谱访问Stackelberg游戏：友好的干扰干扰通信对抗

防御和进攻能力在交流对抗游戏中都非常重要。通过利用以上两个功能，设计了在两个相对的团队之间的频谱对抗机制，这两个相对的团队称为蓝队（BT）和红队（RT）。基本思想是通过牺牲盟友的部分表现来严重恶化对手的沟通。具体地说，部署了友好而智能的干扰器（假设在BT中），以削弱对手（即RT中的成员）的通信，而不会对其他BT成员造成严重损害，而智能RT成员则在规避干扰并减轻相互干扰。友好干扰机和其他节点之间的交互被建模为Stackelberg游戏，每个玩家都在寻求各自的效用最大化。我们证明每个子游戏都是确切的潜在游戏。为了有效地寻找平衡解，提出了一种并行对数线性学习算法，基于该算法，每个用户可以智能地决定其频谱访问策略。数值结果表明：1）RT通信得到有效抑制。同时，大大减轻了同盟BT通信对之间的相互干扰。2）提出的算法达到了接近最优的解决方案；3）与当前的解决方案状态（即随机选择，随机学习自动机）相比，我们的算法在效用和收敛性方面均表现更好。基于此，每个用户可以智能地决定其频谱访问策略。数值结果表明：1）RT通信得到有效抑制。同时，大大减轻了同盟BT通信对之间的相互干扰。2）提出的算法达到了接近最优的解决方案；3）与当前的解决方案状态（即随机选择，随机学习自动机）相比，我们的算法在效用和收敛性方面均表现更好。基于此，每个用户可以智能地决定其频谱访问策略。数值结果表明：1）RT通信得到有效抑制。同时，大大减轻了同盟BT通信对之间的相互干扰。2）提出的算法达到了接近最优的解决方案；3）与当前的解决方案状态（即随机选择，随机学习自动机）相比，我们的算法在效用和收敛性方面均表现更好。