Frequency agility multi-radar cooperative anti-interference method based on reinforcement learning

The invention discloses a frequency agility multi-radar cooperative anti-interference method based on reinforcement learning, and the method comprises the steps: firstly building a target echo model and an interference signal model according to a phased array radar signal processing flow, taking each radar as an intelligent agent, modeling a radar cooperative anti-interference process as a generalized Markov decision process, and carrying out the recognition of the radar cooperative anti-interference process; and obtaining a state value function, solving the problem by using a proposed parallel multi-agent Q learning algorithm, and finally obtaining a radar carrier frequency selection strategy. According to the method, the appropriate frequency band of the radar can be selected by looking up the table according to the current frequency band of the interference, so that the possible frequency band of the interference at the next moment is avoided, and the multi-radar cooperative anti-interference process is mo