Guangquan Zhang
Papers
4
Total Citations
29
H-Index
3
About
Guangquan Zhang is a leading researcher at the forefront of reinforcement learning and cyber-physical systems, with a particular focus on tackling decision-making under uncertainty. His pioneering work in Bayesian deep reinforcement learning, notably through the integration of deep kernel learning, has provided a robust framework for agents to optimize long-term rewards in complex, unknown environments. Zhang’s major contributions extend to addressing the critical challenge of nonstationary environments, where he has developed novel DRL methods capable of adapting to unknown change points—a breakthrough with profound implications for real-world applications like industrial robotics. His research has garnered significant attention, with his most-cited paper accumulating 13 citations and his work on nonstationary environments already reaching 8 citations since 2024. Beyond reinforcement learning, Zhang has made notable strides in brain-computer interfaces, designing a motor imagery-based BCI system optimized via swarm intelligence, and in modeling cyber-physical systems through spatio-temporal Petri nets. His interdisciplinary approach, combining theoretical rigor with practical application, positions him as a key figure in advancing autonomous systems and human-machine interaction.
Research Focus
Key Achievements
Top Papers
- 1Bayesian Deep Reinforcement Learning via Deep Kernel Learning13 citations · 2018
- 2
- 3
- 4