About me

Hi! Welcome to my website. I started as a PhD student in the Industrial Engineering and Operations Research department of Columbia University. I work with the fabulous Shipra Agrawal. I am excited by research questions under the broad umbrella of reinforcement learning and strategic behavior.

In 2021, I graduated from the University of Illinois Urbana-Champaign with a Master in Computer Science, where I was part of Nan Jiang’s RL theory group.

Selected Papers

• Optimistic Q-learning for average reward and episodic reinforcement learning
  Priyank Agrawal, Shipra Agrawal. Accepted to Conference on Learning Theory (COLT) 2025.

• Q-learning with Posterior Sampling
  Priyank Agrawal, Shipra Agrawal, Azmat Azati. Under review.

• On the Convergence of Single-Timescale Actor-Critic
  Navdeep Kumar, Priyank Agrawal, Giorgia Ramponi, Kfir Yehuda Levy, Shie Mannor. Under review.

• Policy Gradient with Tree Search (PGTS)
  Navdeep Kumar, Priyank Agrawal, Kfir Yehuda Levy, Shie Mannor. ICLR Tiny Papers Track, 2025.

• Learning-Augmented Mechanism Design: Leveraging Predictions for Facility Location
  Priyank Agrawal, Eric Balkanski, Vasilis Gkatzelis, Tingting Ou, and Xizhi Tan ACM EC 2022; extended version accepted to Mathematics of Operations Research.

• A Tractable Online Learning Algorithm for the Multinomial Logit Contextual Bandit
  Priyank Agrawal, Theja Tulabandhula, Vashist Avadhanula. European Journal of Operational Research.

• Full paper list: Google Scholar