Runfei Luo
Papers
1
Total Citations
22
H-Index
1
About
Runfei Luo is a researcher advancing the intersection of reinforcement learning (RL) and online stochastic optimization. Their most cited work, "ORL: Reinforcement Learning Benchmarks for Online Stochastic Optimization Problems" (2019, 22 citations), introduces a novel benchmark framework that applies state-of-the-art RL algorithms to canonical operational challenges—specifically Bin Packing, Newsvendor, and Vehicle Routing problems. This contribution bridges the gap between theoretical RL advances in robotics and games and their practical deployment in logistics, supply chain, and inventory management. By systematically evaluating RL methods on these classic optimization tasks, Luo provides a standardized testbed that enables fair comparison and drives progress in data-driven decision-making under uncertainty. Their work is particularly notable for demonstrating how deep RL can adapt to dynamic, real-world constraints where traditional heuristics fall short. With growing recognition in the operations research and machine learning communities, Luo’s research continues to shape how autonomous systems learn to solve complex, sequential decision problems in stochastic environments.
Research Focus
Key Achievements
Top Papers
- 1