Method for designing ethical agent based on reinforcement learning

A technology of reinforcement learning and intelligent agents, applied in the field of machine learning, can solve the problems of driverless cars out of control and death, and achieve the effects of strong ethical judgment ability, generality assurance, and time saving

Pending Publication Date: 2021-09-17
GUILIN UNIV OF ELECTRONIC TECH +1
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, a robot misidentifies a worker as a steel plate cutter, a smart speaker advises its user to commit suicide, a driverless car goes out of control and kills a person, etc.

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
  • Method for designing ethical agent based on reinforcement learning
  • Method for designing ethical agent based on reinforcement learning
  • Method for designing ethical agent based on reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals designate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

[0042] see Figure 1 to Figure 9 , the present invention provides a method for designing ethical agents based on reinforcement learning, including:

[0043] S1 summarizes and extracts meta-ethical behaviors from codes of conduct;

[0044] The code of conduct is the daily code of conduct for primary and middle school students. The daily code of conduct for primary and middle school students is the daily code of conduct for middle school students compiled by the Ministry of Education, which plays an important role in the developm...

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 relates to the field of machine learning, and discloses a method for designing an ethical agent based on reinforcement learning, which comprises the following steps of: concluding and extracting meta ethical behaviors from behavior specifications; grading the element ethical behaviors by utilizing a crowdsourcing technology to obtain element ethical behavior grades; designing a reward mechanism based on a trajectory tree, a meta-ethical behavior hierarchical design and a reinforcement learning algorithm; and selecting a life scene and carrying out ethical agent training by utilizing a reward mechanism. Similar behaviors in different scenes are summarized, various behaviors in daily life of people can be summarized generalized, the generality of the environment is ensured, and the problem that the scenes are limited is solved to a certain extent; graded statistics is performed on meta-ethical behaviors through a crowdsourcing technology, so that the time cost can be saved; through combination of meta-ethical behavior classification and a trajectory tree, a reward and punishment mechanism in reinforcement learning is improved, and possible human behaviors are efficiently coped with.

Description

technical field [0001] The invention relates to the field of machine learning, in particular to a method for designing an ethical agent based on reinforcement learning. Background technique [0002] With the rapid development of science and technology, artificial intelligence has been widely used in many fields such as medical care, transportation, and finance. Various forms of intelligent agents such as intelligent nursing robots and self-driving cars are also playing an increasingly important role in human life. However, when human beings enjoy the convenience brought by artificial intelligence, they also need to solve the ethical problems it brings. For example, a robot misidentifies a worker as a steel plate cutter, a smart speaker advises its user to commit suicide, and a driverless car loses control and kills a person. Therefore, how to ensure that the agent has the ability to abide by the basic ethical norms of human beings and interact appropriately and friendly wit...

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): G06N20/00
CPCG06N20/00
Inventor 古天龙高慧李龙包旭光李云辉
Owner GUILIN UNIV OF ELECTRONIC TECH
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