Publications

“On the Convergence Rates of Log-Linear Policy Gradient Methods” [PDF], Matin Aghaei, Anderson de Andrade, Qiushi Lin, Sharan Vaswani. In preparation.

“Practical Principled Policy Optimization for Finite MDPs” [PDF], Michael Lu, Matin Aghaei, Anant Raj, Sharan Vaswani. “Optimization for Machine Learning” workshop, NeurIPS, 2023 (Oral Presentation).