Dhruv Rohatgi

PhD student, Massachusetts Institute of Technology

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 1

1 paper

Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable RL

#510 Spotlight · Yuda Song, Dhruv Rohatgi, Aarti Singh, Drew Bagnell

Through theoretical models and empirical testbeds, we characterize the algorithmic tradeoff between privileged expert distillation and RL, and better options for expert distillation.