Qiaomin Xie

Papers

Total Citations

H-Index

About

Qiaomin Xie is a rising researcher whose work lies at the intersection of reinforcement learning, Monte-Carlo planning, and operations research. Her most influential contribution, "POLY-HOOT," tackles the challenging problem of Monte-Carlo planning in continuous state-action spaces—a domain where traditional methods like MCTS struggle. By providing a non-asymptotic analysis and a provably efficient algorithm, she has helped bridge the gap between theoretical guarantees and practical deployment in real-world, high-dimensional environments. This work has garnered 6 citations and is foundational for researchers pushing beyond discrete planning. Xie is also the lead creator of ORSuite, an open-source library that brings reinforcement learning tools to the operations research community. Unlike RL libraries focused on games or robotics, ORSuite provides environments, algorithms, and instrumentation specifically designed for decision-making in logistics, scheduling, and resource allocation. With 3 citations, it is already enabling reproducible, domain-relevant experimentation. Through both theoretical rigor and practical tool-building, Qiaomin Xie is shaping how continuous-space planning and operations-focused RL are studied and applied—making her a key voice for students and researchers at the frontier of intelligent decision-making.