Enxin Sun
Papers
1
Total Citations
23
H-Index
1
About
Enxin Sun is a researcher advancing the frontiers of safe reinforcement learning (RL), with a primary focus on integrating chance-constrained optimization into model-based RL frameworks. Their most cited work, "Model-Based Chance-Constrained Reinforcement Learning via Separated Proportional-Integral Lagrangian" (2022, 23 citations), introduces a novel approach to ensuring safety under uncertainty—a critical challenge for deploying RL in real-world applications like robotics and autonomous systems. By proposing a separated proportional-integral Lagrangian method, Sun addresses the limitations of traditional penalty and Lagrangian techniques, enabling more reliable handling of probabilistic constraints. This contribution is particularly impactful for students and researchers working on safety-critical RL, as it provides a principled way to balance performance and risk. Sun’s work stands out for its rigorous theoretical grounding and practical relevance, offering a pathway toward safer AI systems. With growing recognition in the RL community, their research continues to influence the development of robust, constraint-aware algorithms, making Enxin Sun a notable voice in the quest for trustworthy autonomous decision-making.
Research Focus
Key Achievements
Top Papers
- 1