Distributed multi-agent deterministic strategy control method for large complex system

Abstract

The invention discloses a method for determining a node control target of each intelligent agent corresponding to each control node in a large complex system. The method comprises the following stepsof setting a reward function of each intelligent agent; determining an action set corresponding to the action of the intelligent agent in the current control period, obtaining an experience set basedon the action set and an environment reward set corresponding to the reward function, storing the experience set to an experience buffer area, and updating the initialization state; training the intelligent agent according to the experience buffer area until the whole intelligent agent is traversed; and repeating the step of determining the action set corresponding to the action of the intelligentagent in the current control period until all the intelligent agents are traversed to obtain a target deep strategy network. According to the method, a distributed multi-agent control method is adopted in a large complex system, a plurality of agents are constructed and share information with one another, and the agents are continuously optimized and the control performance is improved in the training process according to the control targets of the agents.

Description

technical field [0001] The present application relates to the technical field of large-scale complex system operation control, and specifically relates to a large-scale complex system distributed multi-agent deterministic strategy control method. Background technique [0002] A system composed of a large number of individual agents and their connections can be called a multi-agent network. In this framework, the information collected by each member is local and scattered, and they do not have the ability to complete the entire task independently, that is, individuals cannot exchange information to make the state quantities of all members tend to be equal, so they cannot pass Collaborate on complex tasks in large and complex systems. Contents of the invention [0003] In order to solve the above problems, an embodiment of the present application provides a deterministic strategy control method for distributed multi-agents in a large complex system. [0004] In the first a...

AI Technical Summary

Problems solved by technology

In this framework, the information collected by each member is local and scattered, and they do not have the ability to complete the entire task independently, that is, individuals cannot exchange information to make the state quantities of all members tend to be equal, so they cannot pass Collaborate on complex tasks in large complex systems

Images