Zhaoxiang Zang
Papers
1
Total Citations
2
H-Index
1
About
Zhaoxiang Zang is a researcher whose work lies at the intersection of machine learning, evolutionary computation, and knowledge discovery. His primary focus has been on advancing Learning Classifier Systems (LCS), particularly the accuracy-based XCS model, to tackle complex, non-Markovian decision-making problems. In his notable 2013 paper, "Knowledge extraction and rule set compaction in XCS for non-Markov multi-step problems," Zang introduced novel methods for extracting interpretable, compact rule sets from XCS, enabling the system to handle environments with hidden states and partial observability. This contribution is critical for bridging the gap between high-performance reinforcement learning and human-understandable knowledge representation. While his citation count for this work is modest, the research addresses a fundamental challenge in explainable AI and adaptive systems. Zang’s work is particularly valuable for students and researchers interested in evolutionary machine learning, transparent AI, and the practical deployment of LCS in real-world sequential decision tasks.
Research Focus
Key Achievements
Top Papers
- 1