Lingwei Zhu

Nara Institute of Science and Technology

Papers

2

Total Citations

22

H-Index

2

About

Lingwei Zhu is a researcher advancing the frontiers of safe and sample-efficient reinforcement learning (RL), with a focus on bridging the gap between simulation and real-world robotics. His work addresses two critical challenges: ensuring safety under strict physical constraints and enabling scalable sim-to-real transfer. In his highly cited 2023 paper, "Cyclic policy distillation," Zhu introduced a novel method that combines domain randomization with knowledge distillation to achieve sample-efficient sim-to-real RL, demonstrating that policies trained in simulation can be reliably deployed on real robots with minimal data. This work has already garnered 16 citations, reflecting its impact on the robotics and RL communities. Earlier, in "Dynamic Actor-Advisor Programming for Scalable Safe Reinforcement Learning" (2020), he tackled the problem of safe exploration in high-dimensional systems with complex constraints—a domain where few scalable solutions existed. By proposing a framework that dynamically balances performance and safety, Zhu provided a pathway for deploying RL on real-world robots without risking costly failures. His contributions are pivotal for autonomous systems that must operate reliably under uncertainty, making his research essential reading for students and engineers working on safe, deployable AI.

Research Focus

Key Achievements

2
H-Index
2
Papers
22
Total Citations
11
Avg Citations/Paper
🏆 Most Cited Paper
Cyclic policy distillation: Sample-efficient sim-to-real reinforcement learning with domain randomization
16 citations · 2023
📈 Most Prolific Year: 2023 (1 Papers)
🤝 Key Collaborators: 4
🏛 Institutions: Nara Institute of Science and Technology

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago