本文为美国弗吉尼亚理工大学（作者：Ersin S. Selvi）的硕士论文，共117页。

射频电磁频谱是一种宝贵的资源，用户和运营商都可以在这些频段内工作。美国联邦频谱拍卖会腾出部分频谱用于共享。这意味着频谱将变得更加密集；同样数量的频谱将拥有更多的设备和用户。该频谱的设备和平台需要更具适应性和灵活性，以便（1）不受其他系统的干扰，（2）对其他系统造成干扰，（3）继续满足用户（如手机用户）和运营商（如军用雷达）的需求。本文采用马尔可夫决策过程和强化学习来解决这一问题。

The radio-frequency electromagnetic spectrum is a precious resource, in which users and operators are assigned frequency slots in which they can operate. The federal spectrum auction in the United States freed up some of the spectrum for shared use. The implications of this are the spectrum will become more dense; there will be more devices and users in the same amount of spectrum. The devices and platforms of this spectrum need to be more adaptive and agile in order to (1) not be interfered by other systems, (2) cause interference to other systems, and (3) continue to meet the needs of users (e.g. cell phone users) and operators (e.g. military radar). The work presented in this thesis applies Markov decision process and reinforcement learning to solve the problem.

1.       引言

2. 雷达简介

3. 认知雷达与机器学习简介

4. 系统模型与详细方法

5. 实验结果与分析

6. 结论

附录A 干扰案例分析

附录B 训练与测试算法

更多精彩文章请关注公众号：