Guangrun Wang
Papers
1
Total Citations
2
H-Index
1
About
Guangrun Wang is a leading researcher in reinforcement learning and robotics, with a focus on advancing adaptive control systems for complex locomotion. His work centers on developing dynamic policy gradient optimization methods that enable bipedal robots to navigate challenging, non-static environments—a domain where traditional control strategies often falter due to intricate dynamics and multi-criterion optimization demands. Wang’s key contribution lies in his reward-adaptive reinforcement learning framework, which intelligently adjusts reward structures during training to improve stability and efficiency in real-time decision-making. This approach has been instrumental in bridging the gap between simulation and physical robot deployment, offering more robust solutions for bipedal locomotion. His most cited paper, “Reward-Adaptive Reinforcement Learning: Dynamic Policy Gradient Optimization for Bipedal Locomotion” (2021, 2 citations), exemplifies his innovative methodology and has laid groundwork for future research in adaptive robotics. Wang’s work is particularly notable for its practical impact, addressing core challenges in autonomous systems and inspiring new directions in machine learning for embodied agents. His contributions continue to influence students and researchers exploring the frontiers of robotic control and reinforcement learning.
Research Focus
Key Achievements
Top Papers
- 1