Ming-liang XU
Papers
1
Total Citations
6
H-Index
1
About
Ming-liang Xu is a researcher specializing in reinforcement learning and fuzzy systems, with a particular focus on bridging the gap between continuous state-action spaces and adaptive decision-making. His most-cited work, "Fuzzy Q-learning in continuous state and action space" (2010), has garnered 6 citations, establishing a foundational approach for integrating fuzzy logic with Q-learning to handle complex, real-world environments where discrete methods fall short. This contribution is notable for its practical implications in robotics and control systems, offering a more flexible and robust framework for autonomous agents. Xu's research addresses critical challenges in machine learning, particularly in scaling reinforcement learning to continuous domains—a key hurdle in artificial intelligence. While his citation count reflects the niche but growing interest in this area, his work has influenced subsequent studies on hybrid learning algorithms. Xu continues to explore the intersection of computational intelligence and adaptive systems, making his contributions valuable for students and researchers seeking to understand how fuzzy logic can enhance reinforcement learning in dynamic, continuous settings.
Research Focus
Key Achievements
Top Papers
- 1Fuzzy Q-learning in continuous state and action space6 citations · 2010