Papers
1
Total Citations
2
H-Index
1
About
Guofu Wu is a researcher whose work lies at the intersection of multi-agent reinforcement learning and swarm robotics, with a particular focus on collaborative decision-making in non-deterministic environments. His most-cited paper, "Multi-agent Reinforcement Learning with Biased Experience Sharing in Swarm-robotics Domain" (2019), addresses a critical challenge in multi-robot systems: how to effectively share learning experiences among agents to accelerate convergence and improve policy robustness. Wu introduced a novel biased experience sharing mechanism that selectively prioritizes high-value experiences from other agents, enabling more efficient learning in complex, dynamic settings. This contribution has been recognized with 2 citations, demonstrating its relevance to the growing field of distributed robotic intelligence. His work bridges the gap between theoretical reinforcement learning and practical swarm applications, offering scalable solutions for tasks such as collective exploration and cooperative manipulation. Wu’s research is particularly valuable for students and researchers interested in the intersection of machine learning and robotics, as it provides a principled framework for tackling the credit assignment problem in multi-agent systems.
Research Focus
Key Achievements
Top Papers
- 1