Institution: Sungkyunkwan University
Advisor: Prof. Woocheol Choi, Prof. Jeonggyu Huh
Period: 2025
Overview
This project investigated the use of Regularized Direct Policy Optimization (RDPO) as a reinforcement learning approach for solving linear quadratic control (LQR) problems.
The performance of RDPO was evaluated and compared against classical optimal control solutions.
Contributions
- Implemented the RDPO algorithm for LQR problems