Chi-Guhn Lee
Papers
1
Total Citations
9
H-Index
1
About
Chi-Guhn Lee is a leading researcher in reinforcement learning and decision-making under uncertainty, with a focus on developing algorithms that are both sample-efficient and risk-aware. His major contributions lie at the intersection of transfer learning and risk-sensitive optimization, where he has pioneered methods to enable agents to reuse knowledge across tasks while accounting for variability in outcomes. His influential work, "Risk-Aware Transfer in Reinforcement Learning using Successor Features" (2021), which has garnered 9 citations, introduces a framework that combines successor features with risk metrics, allowing for efficient policy adaptation without sacrificing safety or performance. This research addresses a critical bottleneck in practical RL—balancing exploration and exploitation in high-stakes environments. Beyond this, Lee’s broader portfolio explores utility-based optimization and robust decision-making, with applications in operations research and autonomous systems. His work is recognized for bridging theoretical rigor with real-world applicability, making him a key figure in advancing RL toward reliable deployment. For students and researchers, Lee’s contributions offer a roadmap for building intelligent agents that learn faster and act more cautiously in uncertain settings.
Research Focus
Key Achievements
Top Papers
- 1Risk-Aware Transfer in Reinforcement Learning using Successor Features9 citations · 2021