Collaborative multi-agent reinforcement learning method

A reinforcement learning, multi-agent technology, applied in neural learning methods, neural architecture, biological neural network models, etc., can solve the problem of centralized structure affecting the effectiveness of reward distribution mechanism, and achieve the effect of relaxing unreasonable assumptions

Pending Publication Date: 2021-02-12
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF0 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, the reward distribution method in the above algorithm is completely unsupervised, and the expressive

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
  • Collaborative multi-agent reinforcement learning method
  • Collaborative multi-agent reinforcement learning method
  • Collaborative multi-agent reinforcement learning method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention will be further explained below in conjunction with the accompanying drawings and specific embodiments. The embodiments described in the present invention are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, other embodiments obtained by persons of ordinary skill in the art without making creative efforts all fall within the protection scope of the present invention.

[0040] Such as Figure 1-4 As shown, a kind of cooperative multi-agent reinforcement learning method described in the present invention is special in that: a simple and efficient reward highway network algorithm model is designed to test multi-agent cooperative control. This new method has optimization The cost is low, the required sampling cost is low, and it is easy to extend to the situation with a large number of agents.

[0041] The algorithmic model of the reward highway network includes the following s...

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 collaborative multi-agent reinforcement learning method. The method comprises the following steps: obtaining observation information of each agent and a global state of a system; transmitting the obtained observation information of each intelligent agent into a deep neural network to calculate and obtain state action values of all actions of the intelligent agent; performing action selection by utilizing a greedy rule; transmitting the state action value corresponding to the adopted action and the global observation information into a reward highway network; rewardingthe highway network to perform information fusion and inputting a combined state action value; and performing gradient back transmission by utilizing a reward signal given by the environment and updating parameters of the neural network so as to obtain a strategy model of each intelligent agent. The data volume required in the training process of the multi-agent system can be reduced, and the invention is suitable for being popularized to large-scale multi-agent systems.

Description

technical field [0001] The invention belongs to the field of automatic control, in particular to a collaborative multi-agent reinforcement learning method. Background technique [0002] Many problems in the real world can be regarded as cooperative multi-agent problems, such as: UAV swarm control, multi-player video games, control of sensor networks, etc. The use of reinforcement learning algorithms to control multi-agent systems has also been widely used in the above fields. However, collaborative multi-agent reinforcement learning algorithms face three main challenges that make it difficult to achieve good results in complex scenarios. The first is that the joint action space of agents explodes exponentially with the increase of the number of agents, which makes the direct application of single-agent control algorithms to multi-agent systems bring the curse of dimensionality. Second, the environment of a multi-agent system often only gives a global feedback signal corres...

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): G06N3/04G06N3/08
CPCG06N3/084G06N3/045
Inventor 谭晓阳姚兴虎
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap