In-Chang Baek
Papers
1
Total Citations
4
H-Index
1
About
In-Chang Baek is a researcher advancing the frontiers of offline reinforcement learning (RL), a critical paradigm for deploying RL in high-stakes domains like healthcare, autonomous vehicles, and robotics where real-time interaction is costly or dangerous. His most-cited work introduces a "Swapping Target Q-Value Technique" for data augmentation in offline RL, addressing the fundamental challenge of learning effective policies from fixed, limited datasets. By cleverly manipulating target Q-values during training, Baek’s method enables more robust policy development without requiring additional environment interaction—a breakthrough that bridges the gap between online and offline RL performance. His research directly tackles the data scarcity problem that has long hindered practical RL applications, offering a computationally efficient solution that enhances sample efficiency and policy stability. With 4 citations on his seminal 2022 paper, Baek’s contributions are gaining traction among researchers seeking to make RL viable for real-world deployment. His work stands out for its elegant simplicity and practical impact, positioning him as an emerging voice in the offline RL community. For students and researchers, Baek exemplifies how targeted algorithmic innovations can unlock the potential of reinforcement learning in data-constrained environments.
Research Focus
Key Achievements
Top Papers
- 1