Unlock instant, AI-driven research and patent intelligence for your innovation.

Reinforcement learning algorithm for cooperative communication and control of multi-agent system

A multi-agent system, collaborative communication technology, applied in transmission systems, machine learning, computing, etc., can solve problems such as differential equations describing agents

Inactive Publication Date: 2021-03-02
SOUTHEAST UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the kinematic characteristics of the agent are relatively complex and the sensor data dimension is high, it is difficult to describe the agent using differential equations, so that the existing methods based on control theory cannot be used for control.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Reinforcement learning algorithm for cooperative communication and control of multi-agent system
  • Reinforcement learning algorithm for cooperative communication and control of multi-agent system
  • Reinforcement learning algorithm for cooperative communication and control of multi-agent system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] Below in conjunction with accompanying drawing and specific embodiment the present invention is described in further detail:

[0061] The invention provides a reinforcement learning algorithm for collaborative communication and control of a multi-agent system. The method provides a reinforcement learning algorithm for a multi-agent system that sends and receives messages through a communication network with a certain topology for information sharing. Algorithms enable the multi-agent system to build communication strategies and control strategies on each agent through training, so that the entire multi-agent system can achieve efficient information sharing and finally complete the task of collaborative control.

[0062] The following describes an embodiment in which the method disclosed in the present invention is applied to a multi-agent system composed of three mobile robots and performs cooperative control.

[0063] figure 1 It is the composition structure and infor...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a reinforcement learning method for communication and control of a multi-agent system. According to the method, a reinforcement learning algorithm is provided for a multi-agentsystem which performs information sharing by sending and receiving messages through a communication network with a certain topological structure, so that the multi-agent system can construct a communication strategy and a control strategy on each agent through training; effective low-dimensional communication information is extracted from high-dimensional original input of sensing equipment by the intelligent agent, so that efficient information sharing and cooperative control of the whole multi-intelligent-agent system can be achieved. According to the method, the complexity of communicationand control strategy design of the multi-agent system with complex dynamic and high-dimensional observation is reduced, and meanwhile, the communication load between agents is also reduced.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence and machine learning, and relates to a reinforcement learning algorithm for cooperative communication and control of a multi-agent system. Background technique [0002] A multi-agent system is composed of multiple interacting agents, each of which has certain sensing, computing and execution capabilities, and can communicate with other agents through a communication network. The goal of multi-agent cooperative communication and control is to make multiple agents cooperate with each other by designing reasonable communication and control strategies, and then complete tasks that a single agent cannot complete independently. The agents in the multi-agent system can be embodied as different entities in practical applications in different fields, such as aircraft, mobile robots, traffic lights, power network nodes, etc. It plays an important role in applications such as flight, mobile ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06N3/04G06N20/00H04L29/08
CPCG06N20/00H04L67/10G06N3/045
Inventor 王远大孙长银孙佳
Owner SOUTHEAST UNIV