Siyuan Li
Papers
1
Total Citations
2
H-Index
1
About
Siyuan Li is a leading researcher at the intersection of explainable artificial intelligence and deep reinforcement learning (DRL), with a particular focus on long-horizon control tasks. Their most influential work, "SkillTree," introduces a groundbreaking framework that replaces the opaque neural network policies of traditional DRL with transparent, skill-based decision trees. This innovation directly addresses the critical challenge of interpretability in safety-critical and human-agent interaction domains, where understanding an agent's decision-making process is paramount. By decomposing complex tasks into explainable, hierarchical skills, Li’s approach not only enhances transparency but also improves sample efficiency and generalization in long-horizon scenarios. With over 2 citations on this recent 2025 publication, their work is already shaping the next generation of trustworthy autonomous systems. Li’s contributions are pivotal for students and researchers seeking to bridge the gap between high-performance DRL and the practical need for verifiable, human-understandable AI behavior in real-world applications.
Research Focus
Key Achievements
Top Papers
- 1