David Snyder

PhD Student in the IRoM Lab at Princeton University, working on safety and generalization assurances for robots.

[David Snyder @das_princeton]

(12/12) For more information and additional results, please see:

Project Page: https://t.co/OcUf9gY0Br

Paper: https://t.co/3F42i4YVd5

Code: https://t.co/oiOuhK46gI

[David Snyder @das_princeton]

(1/12) How should we rigorously compare robot policies? Comparison is central to robotics research, but is inherently expensive. We introduce NSCORE, a flexible, general-purpose, and data-efficient method for rigorous policy comparison. Accepted to RSS 2026.

[David Snyder @das_princeton]

(11/12) [Acknowledgments] This work is undertaken with my incredible collaborators @ApurvaBadithela @NikolaiMatni @pappasg69 @Majumdar_Ani @MashaItkina and @imp_aa.

[David Snyder @das_princeton]

(13/13) Very grateful to Haruki Nishimura and Masha Itkina in the TLU (Trustworthy Learning under Uncertainty) team at the Toyota Research Institute (TRI), as well as many additional collaborators at TRI and in the IRoM Lab at Princeton!

[David Snyder @das_princeton]

(1/13) How should we rigorously compare robot policies? Comparison is central to robotics research, but is inherently expensive. We introduce STEP, a flexible and data-efficient method for statistically rigorous policy comparison.

Accepted at RSS 2025: https://t.co/MtAMIwlbAn

[David Snyder @das_princeton]

(12/13) For more information —

Project Page: https://t.co/MtAMIwlbAn
Paper: https://t.co/ps9lQM8WxJ
Code: coming soon! (link on project page)