Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Multi-agent adversarial decision-making method based on cooperative reinforcement learning and transfer learning

A technology of reinforcement learning and transfer learning, applied in neural learning methods, inference methods, biological neural network models, etc. Number disaster problem, reduce loss, avoid the effect of randomness

Active Publication Date: 2020-09-22
航天欧华信息技术有限公司
View PDF3 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Based on the problems mentioned in the background technology, the present invention proposes a multi-agent confrontation decision-making method based on cooperative reinforcement learning and transfer learning, which overcomes the slow convergence speed and poor scene adaptability in the traditional method, and it is difficult to complete the scheduled decision efficiently. The deficiencies of the task; its specific technical content is as follows:

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
  • Multi-agent adversarial decision-making method based on cooperative reinforcement learning and transfer learning
  • Multi-agent adversarial decision-making method based on cooperative reinforcement learning and transfer learning
  • Multi-agent adversarial decision-making method based on cooperative reinforcement learning and transfer learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] Attached as follows figure 1 , to further describe the application scheme:

[0047] The present invention proposes a multi-agent confrontation decision-making method based on cooperative reinforcement learning and transfer learning, which is divided into two aspects: cooperative reinforcement learning and transfer learning, including the following steps:

[0048] Step 1. Use the visual perception equipment of the agent to obtain the current environment information, and use the current task environment information to define the state space of the agent. If the current state space is continuous, the state space needs to be discretized. Use the method of linear segmentation to discretize the continuous state space into a discrete state space, denoted as S={s 1 ,s 2 ,...,s n}.

[0049] Step 2. After obtaining the perception information of the external environment through step 1, set the action space of the agent. In a complex real-time control environment, the action ...

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 provides a multi-agent adversarial decision-making method based on cooperative reinforcement learning and transfer learning, and the method is characterized in that the method comprisesthe following steps: defining the state space S = {s1, s2,..., sn} of an agent; setting an action space A to be equal to {a1, a2,..., an}; setting a value function matrix of the agent reinforcement learning model; calculating a value function sequence corresponding to the current state st by using an action evaluator, and selecting a corresponding action at through an action selector based on simulated annealing and softmax strategy; meanwhile, the state of the intelligent agent is changed, and the intelligent agent is transferred to the next state st + 1. After the action at is executed, theintelligent agent obtains a reward signal rt from the environment; the loss of experience storage can be reduced through a weight sharing mode, and the adversarial decision-making efficiency is improved. Through the migration learning method based on the attenuation function, the agent can reuse previous experience with a gradually decreasing probability, and the migration learning migrates the previously trained action evaluator weight to more adversarial decision scenes, thereby improving the generalization of the learning model.

Description

technical field [0001] The invention belongs to the field of machine learning and intelligent computing, and in particular relates to a multi-agent confrontation decision-making method based on cooperative reinforcement learning and transfer learning. Background technique [0002] With the continuous development of artificial intelligence and intelligent control technology, machine learning has been widely used in many research fields such as intelligent robots, unmanned driving, industrial Internet of Things, and edge computing, and plays an important role. Multi-agent confrontation decision-making is a current research hotspot in the field of intelligent computing. Common multi-agent confrontation decision-making includes robot soccer and underwater robot games. However, as the multi-agent confrontation decision-making environment tends to become more complex and fuzzy, and the task environment has more uncertainties, the classic multi-agent confrontation decision-making m...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06N5/04G06N3/08
CPCG06N5/042G06N3/084
Inventor 冷立雄马占国宫业国
Owner 航天欧华信息技术有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products