Max Robotics — Global Service Robot Directory + US Certification

About

Ke Xue is a researcher specializing in optimization and evolutionary computation, with a particular focus on Bayesian optimization, Quality-Diversity algorithms, and multi-objective reinforcement learning. His work bridges theoretical foundations and practical applications across robotics, experimental design, and decision-making systems. Xue's contributions span several interconnected areas. His early work on Bayesian optimization using pseudo-points advanced the field of efficient black-box optimization, a technique critical for parameter tuning and expensive experimental pipelines. He has made meaningful strides in Quality-Diversity (QD) algorithms, developing novel selection mechanisms through non-surrounded-dominated sorting and providing theoretical proofs that QD algorithms can provably enhance broader optimization performance — a landmark result that strengthens the mathematical legitimacy of evolutionary approaches. More recently, Xue has extended multi-objective thinking into reinforcement learning through Pareto Set Learning, addressing complex real-world scenarios in navigation, robotics, and gaming where competing objectives must be balanced simultaneously. Collectively, his papers have accumulated citations reflecting growing community interest in these intertwined fields. His research is particularly valuable for students and practitioners seeking rigorous yet practical tools for tackling high-dimensional, multi-criteria optimization challenges in modern AI systems.