Chenjun Xiao
Papers
1
Total Citations
3
H-Index
1
About
Chenjun Xiao is a leading researcher in artificial intelligence, specializing in multiagent reinforcement learning, planning under combinatorial action spaces, and efficient decision-making algorithms. His most notable contribution is the development of Multiagent Gumbel MuZero, a groundbreaking framework that extends the MuZero and AlphaZero paradigms to tackle complex multiagent environments with vast combinatorial action sets. This work directly addresses a critical bottleneck in modern AI: the need for excessive simulations to achieve strong policies. By introducing Gumbel-based planning, Xiao’s method dramatically improves sample efficiency and scalability, enabling state-of-the-art performance in domains ranging from board games to robotics. Though his seminal paper has already garnered early citations, its impact is poised to grow as the field seeks more practical, simulation-efficient solutions. Xiao’s research bridges theoretical rigor and real-world applicability, offering a blueprint for deploying advanced planning algorithms in multiagent systems. His work is essential reading for students and researchers aiming to push the boundaries of reinforcement learning and multiagent coordination.
Research Focus
Key Achievements
Top Papers
- 1