Deduction simulation system and method for sea-air cluster confrontation, equipment and storage medium

Abstract

The invention discloses a deduction simulation system and method for sea-air cluster confrontation, equipment and a storage medium, the deduction simulation system deploys a deep reinforcement learning system on a server, deploys simulation systems on a plurality of computing nodes, and the computing nodes are connected with the server through a network, a plurality of simulation system instances run in the simulation system of each computing node, so that a parallel distributed network architecture is constructed, distributed parallelism and acceleration are realized, and good expansibility is achieved. The deep reinforcement learning system can obtain a large amount of sample data from the parallel distributed simulation architecture for training, so that the generation speed of training samples and the learning efficiency of an algorithm are greatly improved, and the simulation system and the deep reinforcement learning system adopt modular design, have good expansibility and are convenient for customized design.

Description

technical field [0001] The present invention relates to the field of wargame simulation technology, in particular, to a simulation system, method, device, and computer-readable storage medium for sea-air swarm confrontation. Background technique [0002] The decision-making control of sea-air swarm confrontation is an important research direction in the field of wargame simulation research. It is a key technology for cross-domain and cross-platform group combat units to complete combat mission objectives. Deep reinforcement learning technology is used to solve the decision-making control of sea-air swarm confrontation Questions are a valid method. However, the current deep reinforcement learning algorithm for sea-air swarm confrontation first needs the research platform to generate a large amount of sample data for algorithm training. If you directly use the actual sea-air equipment to conduct a large number of exercises and experiments to obtain these data, it will not only...

AI Technical Summary

Problems solved by technology

However, the current deep reinforcement learning algorithm for sea-air swarm confrontation first needs the research platform to generate a large amount of sample data for algorithm training. If you directly use the actual sea-air equipment to conduct a large number of exercises and experiments to obtain these data, it will not only cost a lot of money, but also inefficiency , and the risk is extremely high; secondly, the research platform needs to be able to reasonably evaluate the performance of the algorithm, guide the evolution and improvement of the algorithm, and continuously improve the performance of the algorithm until it converges

Images