Guohui Ding
Papers
2
Total Citations
10
H-Index
2
About
Guohui Ding is a researcher specializing in multi-agent reinforcement learning and cooperative robotics, with a focus on enabling teams of robots to work together on complex physical tasks. Their most cited work, "Distributed Reinforcement Learning for Cooperative Multi-Robot Object Manipulation" (2020), has accumulated 10 citations and introduces two pioneering distributed approaches: distributed approximate RL (DA-RL), which uses individual Q-learning with tailored reward functions, and game-theoretic RL (GT-RL), which leverages strategic interaction models. These contributions address the fundamental challenge of coordinating multiple robots without centralized control, making them highly relevant for applications in manufacturing, logistics, and search-and-rescue operations. Ding’s research bridges reinforcement learning theory and practical multi-robot systems, offering scalable solutions that reduce communication overhead while maintaining cooperative performance. Their work is particularly notable for integrating game-theoretic principles into RL, a novel approach that enhances robustness in dynamic environments. By advancing distributed decision-making, Ding has laid important groundwork for future autonomous systems that require seamless human-robot and robot-robot collaboration.
Research Focus
Key Achievements
Top Papers
- 1
- 2