Intelligent planning method for combat resource cross-domain allocation problem

The invention provides an intelligent planning method for a combat resource cross-domain allocation problem. The intelligent planning method comprises the following steps: designing a communication-based multi-agent reinforcement learning combat resource cross-domain allocation solving environment; establishing a proximity strategy optimization network model for cross-domain deployment of multi-agent reinforcement learning combat resources based on communication; training a communication-based multi-agent reinforcement learning combat resource cross-domain deployment proximity policy optimization network model to obtain a trained proximity policy optimization network model; the trained proximity strategy optimization network model is used for testing, and a combat resource cross-domain scheduling problem is solved; and multi-agent combat resource cross-domain deployment deep reinforcement learning network optimization is carried out for application scene changes, and self-learning and online upgrading of the