Wenshuai Zhao

About

Wenshuai Zhao is a researcher advancing the frontier of deep reinforcement learning (DRL), with a focused emphasis on multi-robot systems. His primary research areas include bridging the sim-to-real gap, improving sample efficiency in distributed multi-agent reinforcement learning (MARL), and developing robust algorithms resilient to adversarial agents. Zhao’s most cited work, “Towards Closing the Sim-to-Real Gap in Collaborative Multi-Robot Deep Reinforcement Learning” (2020), has garnered over 33 citations, underscoring its influence in the field. This paper tackles the critical challenge of transferring policies learned in simulation to real-world robotic platforms—a key bottleneck for deploying DRL in practical multi-robot collaboration. By addressing issues of experience efficiency and robustness, Zhao’s contributions help enable more reliable and scalable autonomous systems. His research is particularly relevant for students and engineers working on swarm robotics, autonomous navigation, and distributed control. Through his work, Zhao is helping to lay the groundwork for a future where teams of robots can learn and adapt together in complex, dynamic environments.

Research Focus

Key Achievements

Top Papers

1. 1
   Towards Closing the Sim-to-Real Gap in Collaborative Multi-Robot Deep Reinforcement Learning

   33 citations · 2020
2. 2
   Towards Closing the Sim-to-Real Gap in Collaborative Multi-Robot Deep Reinforcement Learning

   2 citations · 2020

Key Collaborators

Contact & Links