Jiayi Guan
Papers
1
Total Citations
6
H-Index
1
About
Jiayi Guan is a rising researcher in artificial intelligence, with a primary focus on offline reinforcement learning (RL)—a critical area for deploying RL in real-world settings where direct environmental interaction is costly or hazardous, such as robotics and autonomous driving. Guan’s most notable contribution is the development of the "UAC: Offline Reinforcement Learning With Uncertain Action Constraint" framework (2023), which addresses a key challenge in offline RL: ensuring that learned policies remain within the support of the training data to avoid dangerous, out-of-distribution actions. By introducing an uncertain action constraint mechanism, Guan’s work enhances the safety and reliability of offline RL algorithms, making them more practical for high-stakes applications. This paper has already garnered 6 citations, signaling its early impact and relevance in the quickly evolving RL community. Guan’s research bridges the gap between theoretical RL advances and real-world deployment, offering a promising path toward safer autonomous systems. As the field grows, Guan’s contributions are poised to influence both academic research and industrial applications, marking them as a researcher to watch in the coming years.
Research Focus
Key Achievements
Top Papers
- 1UAC: Offline Reinforcement Learning With Uncertain Action Constraint6 citations · 2023