Kang Xu
Papers
1
Total Citations
15
H-Index
1
About
Kang Xu is a researcher whose work sits at the intersection of artificial intelligence, machine learning, and robotics, with a particular focus on autonomous planning and decision-making algorithms. His most notable contribution to date is the development of the Self-Learning Monte Carlo Tree Search algorithm (SL-MCTS), introduced in 2023, which represents a meaningful advancement in intelligent robot path planning. By integrating the classical Monte Carlo Tree Search framework with a novel two-branch Policy-Value Network (PV-Network), Xu's SL-MCTS enables autonomous agents to continuously refine their problem-solving capabilities in single-player environments — a challenging setting that demands both exploration and exploitation without adversarial feedback. This work addresses a longstanding tension in planning algorithms between computational efficiency and solution quality. Garnering 15 citations since its publication, the research has begun attracting attention from the robotics and reinforcement learning communities. Xu's contributions reflect a broader commitment to bridging theoretical AI methodologies with practical robotic applications, positioning him as an emerging voice in the development of adaptive, self-improving autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1A self-learning Monte Carlo tree search algorithm for robot path planning15 citations · 2023