Dong Gu Choi

Dr. Dong Gu Choi


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 November 2020 in Expert Systems with Applications
Verified
Journal Article
Closed access
HPHyungjun Park
Hyungjun Park
MSMin Kyu Sim
Min Kyu Sim
DCDong Gu Choi
Dong Gu Choi

11 June 2024 in Energy
Verified
Journal Article
Closed access
HLHwarang Lee
Hwarang Lee
JAJiseok Ahn
Jiseok Ahn
DCDong Gu Choi
Dong Gu Choi
SPSang Yong Park
Sang Yong Park

1 February 2019 in Energy
Verified
Journal Article
Closed access
HKHansung Kim
Hansung Kim
HCHyungkyu Cheon
Hyungkyu Cheon
YAYoung-Hwan Ahn
Young-Hwan Ahn
DCDong Gu Choi
Dong Gu Choi

28 May 2022 in International Journal of Hydrogen Energy
Verified
Journal Article
Closed access
JCJaewon Choi
Jaewon Choi
DCDong Gu Choi
Dong Gu Choi
SPSang Yong Park
Sang Yong Park

25 October 2019 in Production and Operations Management
Verified
Journal Article
Closed access
PDF file
DCDong Gu Choi
Dong Gu Choi
MLMichael K. Lim
Michael K. Lim
KMKarthik Murali
Karthik Murali
VTValerie Thomas
Valerie Thomas

16 March 2022 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
HPHyungjun Park
Hyungjun Park
DMDaiki Min
Daiki Min
JRJong-Hyun Ryu
Jong-Hyun Ryu
DCDong Gu Choi
Dong Gu Choi
Existing reinforcement learning (RL) methods have limited applicability to real-world industrial control problems because of their various constraints. To overcome this challenge, in this article, we devise a novel RL method to enable the optimization of a policy while strictly satisfying the system constraints. By leveraging a value-based RL approach, our proposed method is not limited by the challenges faced when searching a constrained policy. Our method has two main features. First, we devise two distance-based Q-value update schemes, incentive and penalty updates, which enable the agent to decide on controls in the feasible region by replacing an infeasible control with the nearest feasible continuous control. The proposed update schemes can adjust the values of both continuous and original infeasible controls. Second, we define the penalty cost as a shadow price-weighted penalty to achieve efficient, constrained policy learning. We apply our method to the microgrid control, and the case study demonstrates its superiority.