5 papers
Reinforcement learning with distance-based incentive/penalty (DIP) updates for highly constrained industrial control systems
Hyungjun Park, Daiki Min, Jong-hyun Ryu +1
Typical reinforcement learning (RL) methods show limited applicability for real-world industrial control problems because industrial systems involve various constraints and simulta…
Delayed Q-update: A novel credit assignment technique for deriving an optimal operation policy for the Grid-Connected Microgrid
Hyungjun Park, Daiki Min, Jong-hyun Ryu +1
A microgrid is an innovative system that integrates distributed energy resources to supply electricity demand within electrical boundaries. This study proposes an approach for deri…
An intelligent financial portfolio trading strategy using deep Q-learning
Hyungjun Park, Min Kyu Sim, Dong Gu Choi
Portfolio traders strive to identify dynamic portfolio allocation schemes so that their total budgets are efficiently allocated through the investment horizon. This study proposes…
Algorithms for Determining Birationality of Parametrization of Affine Curves
Hyungju Park
Let be an arbitrary field, and C be a curve in A^n defined parametrically by x_1=f_1(t),...,x_n=f_n(t), where f_1,...,f_n\in k[t]. A necessary and sufficient condition for the…
Homogeneous Cyclotomic Polynomials and Rationality of Curves
Hyungju Park
This paper is withdrawn. The current main theorem can be proved by using a simple field theory. The main theorem is to placed by another theorem, shortly.