Sarah Rathnam

About Me

I am a PhD candidate in Applied Mathematics at Harvard University. I am co-advised by Finale Doshi-Velez of the Data to Actionable Knowledge (DtAK) Lab and Susan Murphy of the Statistical Reinforcement Learning Lab. My research focuses on reinforcement learning in mobile health.

Before my return to academia, I worked for nearly a decade in quantitative finance at various hedge funds and trading firms.

Publications

Sarah Rathnam, Sonali Parbhoo, Weiwei Pan, Susan A. Murphy, and Finale Doshi-Velez. The Unintended Consequences of Discount Regularization: Improving Regularization in Certainty Equivalence Reinforcement Learning. ICML 2023.

Sarah Rathnam, Susan A. Murphy, and Finale Doshi-Velez. Comparison and Unification of Three Regularization Methods in Batch Reinforcement Learning. Workshop on Reinforcement Learning Theory (ICML) 2021.