MingKang Wu
Papers
1
Total Citations
4
H-Index
1
About
Mingkang Wu is a researcher advancing the intersection of reinforcement learning and robotic control, with a primary focus on reward specification for autonomous systems. His most-cited work, "Value of Potential Field in Reward Specification for Robotic Control via Deep Reinforcement Learning" (2023, 4 citations), introduces a novel method that leverages potential fields to design more effective reward functions, a critical challenge in training robust control policies. This approach, demonstrated through both virtual and real-world experiments, helps mitigate issues like sparse rewards and local optima, enabling more reliable learning in complex environments. Wu’s contributions are particularly relevant to aerospace and robotics applications, where precise control is paramount. His work has been presented at major conferences, including a video presentation accessible via the AIAA SciTech Forum. By bridging theoretical reward design with practical robotic deployment, Wu is helping to make deep reinforcement learning more accessible and effective for real-world control tasks, marking him as an emerging voice in the field of intelligent autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1