Zheng Qian

Nanyang Technological University, Nanjing University of Aeronautics and Astronautics

Papers

Total Citations

H-Index

About

Zheng Qian is a researcher whose work bridges reinforcement learning and robotics, with a particular focus on improving stability and efficiency in complex systems. In his 2020 paper "Maximum Entropy Reinforcement Learning with Evolution Strategies," Qian tackled a critical challenge in evolution strategies (ES) for reinforcement learning: their notorious instability. By integrating maximum entropy principles, he proposed a method that enhances robustness while maintaining the low computational cost and scalability that make ES attractive for difficult tasks. This work, which has garnered 6 citations, offers a pathway to more reliable training of agents in dynamic environments. More recently, in 2023, Qian explored human-robot collaboration with his paper "Collaborative workspace design of supernumerary robotic limbs based on multi-objective optimization." Here, he applied multi-objective optimization to design workspaces for extra robotic limbs that augment human capabilities, addressing trade-offs between safety, efficiency, and comfort. With 5 citations, this contribution highlights his ability to translate theoretical advances into practical engineering solutions. Qian’s research is notable for its interdisciplinary approach, combining algorithmic innovation with real-world robotic design, making him a promising voice in the fields of reinforcement learning and assistive robotics.