AI model training method, model using method, computer equipment and storage medium

A model training and model technology, applied in computer parts, computing, computing models, etc., can solve problems such as poor user experience and rigidity of AI models

Active Publication Date: 2020-12-01
超参数科技(深圳)有限公司
View PDF8 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, because the reinforcement learning model only considers the final win or loss, the trained reinforcement learning model is relatively blunt, resulting in poor user experience of the trained AI model

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
  • AI model training method, model using method, computer equipment and storage medium
  • AI model training method, model using method, computer equipment and storage medium
  • AI model training method, model using method, computer equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

[0021] The flow charts shown in the drawings are just illustrations, and do not necessarily include all contents and operations / steps, nor must they be performed in the order described. For example, some operations / steps can be decomposed, combined or partly combined, so the actual order of execution may be changed according to the actual situation.

[0022] It should be understood that the terms used in the specification of this application are for the purpose of ...

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 artificial intelligence, and particularly discloses an AI model training method, a model using method, computer equipment and a storage medium. The method comprises the steps of acquiring multiple sample generation models, performing game according to the multiple sample generation models, and obtaining first game data; acquiring second game data, and traininga to-be-trained model according to the second game data and the first game data, the second game data being real game data; when the to-be-trained model converges, taking the to-be-trained model as ato-be-evaluated model, performing game with a comparison model for multiple times, and obtaining a game result; and when the game result reaches a preset index, determining that the to-be-evaluated model is an AI model, and completing AI model training. The anthropomorphism of a trained reinforcement learning model is improved.

Description

technical field [0001] The present application relates to the field of artificial intelligence, and in particular to an AI model training method, a model using method, computer equipment and storage media. Background technique [0002] With the rapid development of artificial intelligence (AI) technology, in the field of game entertainment, the use of artificial intelligence technology can realize the game between virtual AI and real people, and can beat top professional players. At present, the AI ​​model trained by artificial intelligence technology mainly uses deep reinforcement learning to train the reinforcement learning model for the sake of prediction accuracy and competitive level. However, because the reinforcement learning model only considers the final win or loss, the trained reinforcement learning model is relatively blunt, resulting in poor user experience of the trained AI model. Contents of the invention [0003] The present application provides an AI mode...

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): G06N20/00G06N3/04G06N3/08G06K9/62
CPCG06N20/00G06N3/08G06N3/047G06N3/045G06F18/2415
Inventor 周正季兴李宏亮张正生刘永升
Owner 超参数科技(深圳)有限公司
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