Papers
1
Total Citations
20
H-Index
1
About
Zhaokai Liu is a leading researcher in multiagent reinforcement learning (MARL) and cooperative robotics, with a focus on solving complex, real-world search and coordination problems. His most-cited work, "Cross-Entropy Regularized Policy Gradient for Multirobot Nonadversarial Moving Target Search" (2023, 20 citations), introduces a novel MARL framework that addresses the multirobot efficient search (MuRES) problem. By integrating cross-entropy regularization into policy gradient methods, Liu overcomes key bottlenecks in MARL, enabling teams of robots to collaboratively track and locate moving targets in nonadversarial environments. This contribution is pivotal for applications in disaster response, surveillance, and autonomous exploration, where efficient, decentralized coordination is critical. Liu’s research bridges theoretical advances in reinforcement learning with practical multiagent systems, demonstrating how regularization techniques can stabilize training and improve convergence in cooperative tasks. His work has garnered attention for its innovative approach to scalability and robustness, offering a foundation for future developments in multirobot autonomy. With a growing citation impact, Liu is establishing himself as a rising authority in MARL, pushing the boundaries of how intelligent agents learn to collaborate under uncertainty.
Research Focus
Key Achievements
Top Papers
- 1