Yang Guan

Tsinghua University

Papers

2

Total Citations

42

H-Index

2

About

Yang Guan is a leading researcher in safe reinforcement learning (RL), focused on bridging the gap between theoretical algorithms and real-world, safety-critical applications. His major contributions center on developing principled methods to enforce rigorous safety constraints in RL under uncertainty. In his highly cited work on "Feasible Actor-Critic" (2021, 19 citations), Guan introduced a novel framework that ensures statewise safety—guaranteeing that every visited state meets constraints, rather than just on average—a critical advancement for autonomous driving and robotics. He further advanced the field with "Model-Based Chance-Constrained RL via Separated Proportional-Integral Lagrangian" (2022, 23 citations), which elegantly handles probabilistic safety constraints using a control-theoretic approach, enabling robust performance under model uncertainty. With over 40 total citations on these foundational papers, Guan’s work is recognized for its practical impact, offering scalable solutions that maintain safety without sacrificing task performance. His research is essential reading for students and engineers developing RL systems for high-stakes environments where failure is not an option.

Research Focus

Key Achievements

2
H-Index
2
Papers
42
Total Citations
21
Avg Citations/Paper
🏆 Most Cited Paper
Model-Based Chance-Constrained Reinforcement Learning via Separated Proportional-Integral Lagrangian
23 citations · 2022
📈 Most Prolific Year: 2022 (1 Papers)
🤝 Key Collaborators: 12
🏛 Institutions: Tsinghua University

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago