Xiaotian Liu (刘啸天)
PhD Candidate · Georgia Institute of Technology
I am a PhD candidate in the H. Milton Stewart School of Industrial and Systems Engineering at the Georgia Institute of Technology, advised by Prof. Christos Alexopoulos and Prof. Edwin Romeijn. Before joining Georgia Tech, I received a B.S. in Electronics Engineering from the School of Electronics Engineering and Computer Science at Peking University in 2022 and a B.S. in Management from the Guanghua School of Management at Peking University in 2022.
My research lies at the intersection of operations management and artificial intelligence. I study deep reinforcement learning methods for complex inventory control problems with real-world features, including multi-echelon networks and nonlinear inventory dynamics. I also work on applying machine learning and large language models to broader operations management problems.
I expect to graduate in 2027. I am currently on the job market and am seeking an academic tenure-track position in operations management.
News
| Nov 2026 | I will attend the 2026 INFORMS Annual Meeting, held November 1-4 in San Francisco, California. |
|---|---|
| Aug 2025 | Presented “A Unified Framework for Decision Optimization with Deep Reinforcement Learning and Foundation Models” at the 2025 IEEE International Conference on Automation Science and Engineering in Los Angeles, California. |
| Feb 2025 | Received the 2024 INFORMS Journal on Computing Meritorious Paper Award for “An Efficient Node Selection Policy for Monte Carlo Tree Search with Neural Networks,” the only awarded paper for 2024. |
| Oct 2023 | Presented “A Simulation-Driven Machine Learning Framework for Large-Scale Inventory Management” at the 2023 INFORMS Annual Meeting in Phoenix, Arizona. |
Selected Publications
- Production Planning with Generalized Production Relationships
- Multi-Agent Deep Reinforcement Learning for Multi-Echelon Inventory ManagementProduction and Operations Management Top-20 Most Cited (2023-2026) and Top-10 Most Downloaded (2025).
- An Efficient Node Selection Policy for Monte Carlo Tree Search with Neural NetworksINFORMS Journal on Computing Meritorious Paper (the only awardee in 2024).
- A Simulation-Driven Machine Learning Framework for Large-Scale Inventory Management