Digital Role-Model Twin Using Reinforcement Learning Model 


Vol. 48,  No. 2, pp. 282-293, Feb.  2023
10.7840/kics.2023.48.2.282


PDF
  Abstract

In this paper, we define a digital role model twin as a system that can predict and provide value judgment of a role model, where the 'role model' implies a person the public wants to imitate. To construct digital role model twins, we propose a system that can learn the value judgment of role models using reinforcement learning and enables users to utilize the learned value judgment of role models. Specifically, in the procedure of learning a digital role model twin, decision-making problems are provided to a target role model and the target role model chooses its behavior to the problems. Then, based on contextual information and the role model's behaviors, the role model-specific feature information and preference networks are learned to become a digital role model twin of the target role model. By using the digital role model twin, the users can obtain information about the role model's preference for behaviors to given decision-making problems and contextual information. Through experiments, we demonstrate that the digital role model twin learns the role model's preference appropriately to effectively simulate the role model's preference information.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Related Articles
  Cite this article

[IEEE Style]

J. Kim, H. Je-Gal, S. Lee, H. Lee, "Digital Role-Model Twin Using Reinforcement Learning Model," The Journal of Korean Institute of Communications and Information Sciences, vol. 48, no. 2, pp. 282-293, 2023. DOI: 10.7840/kics.2023.48.2.282.

[ACM Style]

Ji-Wan Kim, Hong Je-Gal, Seung-Jin Lee, and Hyun-Suk Lee. 2023. Digital Role-Model Twin Using Reinforcement Learning Model. The Journal of Korean Institute of Communications and Information Sciences, 48, 2, (2023), 282-293. DOI: 10.7840/kics.2023.48.2.282.

[KICS Style]

Ji-Wan Kim, Hong Je-Gal, Seung-Jin Lee, Hyun-Suk Lee, "Digital Role-Model Twin Using Reinforcement Learning Model," The Journal of Korean Institute of Communications and Information Sciences, vol. 48, no. 2, pp. 282-293, 2. 2023. (https://doi.org/10.7840/kics.2023.48.2.282)
Vol. 48, No. 2 Index

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880