DQN-based agent confrontation behavior implementation method under augmented reality condition

A technology of augmented reality and implementation methods, applied in the information field, can solve problems such as the inflexible behavior of virtual confrontation agents, and achieve the effect of flexible confrontation behavior and high intelligence

Pending Publication Date: 2021-05-14
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In order to solve the problem that the behavior of the virtual confrontation agent in the augmented reality game is not flexible enough, the present invention provides a method for realizing the confrontation behavior of the agent based on DQN under the condition of augmented reality, which can make the confrontation behavior of the virtual agent more flexible

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
  • DQN-based agent confrontation behavior implementation method under augmented reality condition
  • DQN-based agent confrontation behavior implementation method under augmented reality condition
  • DQN-based agent confrontation behavior implementation method under augmented reality condition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] In order to enable those skilled in the art to better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0036] In order to improve the intelligence of NPC in augmented reality applications, the deep reinforcement learning algorithm DQN can be used to train NPC to make it have intelligent behavior. Deep reinforcement learning is one of the emerging technologies in the field of artificial intelligence. It combines the powerful feature extraction ability of deep learning with the decision-making ability of reinforcement learning to realize an end-to-end framework from perceptual input to decision-making output. It has strong learning ability and Wide range of applications. The AI ​​generated by the state machine and behavior tree is too rigid. Human players can easily predic...

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 DQN-based agent confrontation behavior implementation method under an augmented reality condition, and the method comprises the steps: predicting the behaviors of all agents through the powerful feature extraction capability and reinforcement learning decision-making capability of a DQN deep reinforcement learning network, and migrating the agents, which employ the trained DQN network to obtain the actions at all moments to an augmented reality environment. so that the generated virtual agent has higher intelligence, the problem that the behavior of the virtual confrontation agent in the augmented reality game is stiff can be solved, and the effect that the confrontation behavior of the virtual agent is more flexible is achieved.

Description

technical field [0001] The invention belongs to the field of information technology, and in particular relates to a method for realizing an agent confrontation behavior based on DQN under augmented reality conditions. Background technique [0002] With the progress and development of the times, the domestic Internet level has also been improved and extended, especially reflected in the advancement of augmented reality technology. The interaction between users and virtual objects (Non Player Character) is one of the important experience contents of augmented reality applications, so the demand for intelligent and diverse NPCs is more urgent. At present, the main methods of NPC behavior design in augmented reality applications are state machines and behavior trees. Various behaviors of users and NPCs are pre-designed, and NPC behaviors operate according to certain rules, far from real intelligent decision-making. , Evaluation, and learning are far away, that is, AI (Artificia...

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): G06T7/70G06T17/20G06T19/00G06N3/04
CPCG06T7/70G06T17/20G06T19/006G06N3/045
Inventor 陈靖周俊研缪远东
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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