本申请提出了一种基于强化学习实现多监听器的合作主动窃听方法，本申请考虑到每个合法监听器是一个能源受限的设备，在最大干扰功率约束下，进行协作窃听和干扰。即基于强化学习的方法最大化每个合法监听器的期望窃听能效。其中主要涉及的是利用强化学习解决两个合法监听器合作主动窃听的联合干扰功率分配问题。通过两个合法监听器协作发射干扰功率，以实现成功窃听可疑发射器发送的信息，并使每个合法监听器的期望窃听能效最大。

The invention provides a cooperative active eavesdropping method for realizing multiple monitors based on reinforcement learning, which considers that each legal monitor is an energy-limited device and performs cooperative eavesdropping and interference under the constraint of the maximum interference power. That is to say, the expected eavesdropping energy efficiency of each legal monitor is maximized based on a reinforcement learning method. The method mainly relates to solving the problem of joint interference power distribution of cooperative active eavesdropping of two legal monitors by utilizing reinforcement learning. Two legal monitors cooperatively transmit interference power, so that information transmitted by a suspicious transmitter is successfully eavesdropped, and the expected eavesdropping energy efficiency of each legal monitor is maximized.