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

GitHub

GitHub Repository