Xiaoshan Lin
Papers
1
Total Citations
2
H-Index
1
About
Xiaoshan Lin is a researcher whose work lies at the intersection of reinforcement learning, formal methods, and temporal logic. Their primary research focus is on developing principled frameworks for autonomous decision-making under complex, time-sensitive constraints. Lin’s most notable contribution is an automata-theoretic approach for reinforcement learning under probabilistic spatio-temporal constraints with time windows, as detailed in their 2023 paper. This work formulates the problem using a Markov decision process under bounded temporal logic, enabling agents to learn optimal policies while satisfying intricate, real-world constraints. By bridging the gap between formal verification and learning-based control, Lin’s approach addresses critical challenges in robotics and autonomous systems where safety and timing are paramount. While still early in their career, with 2 citations on their most-cited paper, Lin’s work is gaining traction for its innovative integration of temporal logic specifications into RL frameworks. This research lays a strong foundation for future advances in safe, constraint-aware autonomous systems, making Lin a promising voice in the growing field of formal reinforcement learning.
Research Focus
Key Achievements
Top Papers
- 1