Wonjoon Chang
Papers
1
Total Citations
2
H-Index
1
About
Wonjoon Chang is a researcher advancing the frontiers of reinforcement learning (RL), with a focus on improving agent robustness and safety in dynamic environments. His key research areas include domain randomization, safe RL, and autonomous systems. Chang’s most notable contribution, "Balanced Domain Randomization for Safe Reinforcement Learning" (2024), addresses a critical challenge in RL: the tendency of agents to overfit to training environments, limiting their real-world adaptability. By introducing a balanced approach to domain randomization, his work enhances agent generalization while maintaining safety constraints—a vital step for deploying RL in high-stakes applications like robotics and autonomous navigation. Although his work is early in its citation impact (2 citations), it represents a promising direction for bridging the gap between simulated training and real-world deployment. Chang’s research is particularly relevant for students and engineers seeking to build more reliable and transferable AI systems, offering practical solutions to one of RL’s most persistent hurdles.
Research Focus
Key Achievements
Top Papers
- 1Balanced Domain Randomization for Safe Reinforcement Learning2 citations · 2024