Publications

• Rates for offline reinforcement learning with adaptively collected data (L4DC 2025). With D. Qiao, M. Yin, and Y.-X. Wang. Preprint: https://arxiv.org/abs/2306.1406
  
• AKORN: Adaptive knots generated online for regression splines (ICML 2025). With D. Baby and Y.-X. Wang. Code: https://github.com/SunilMadhow/AKORN