Data-Driven Decision-Making Algorithms

Photo by rawpixel on Unsplash

A main research direction for the AIR-DREAM Lab is to develop high-performance, robust, generalizable, and real-world deployable data-driven decision-making algorithms. We are specifically interested in offline policy learning methods, such as offline reinforcement learning (RL), offline imitaiton learning (IL), and offline planning, which enables a simulation-free and low-cost solution to address many real-world problems.

Our current research focus include:

  • Sample-efficient / high-generalization offline RL / IL / planning algorithms
  • Foundation models for decision-making
  • Safe offline RL algorithms
  • Hybrid RL that combines offline and online policy learning
  • Offline policy learning under imperfect reward
  • Feedback-efficient RLHF
Xianyuan Zhan
Xianyuan Zhan
Faculty Member