Abhinav Agarwal — accepted AI-conference papers

2025

Empirical Analysis of Sim-and-Real Cotraining of Diffusion Policies For Planar Pushing from Pixels

Adam Wei, Abhinav Agarwal, Boyuan Chen, Rohan Bosworth, Nicholas Pfaff, Russ Tedrake

IROS 2025

Cotraining with demonstration data generated both in simulation and on real hardware has emerged as a promising recipe for scaling imitation learning in robotics. This work seeks to elucidate basic principles of this simand-real cotraining to inform simulation design, sim-and-real dataset creation,

Cited by 16 Source ↗code ↗Scholar ↗

2022

Stronger Generalization Guarantees for Robot Learning by Combining Generative Models and Real-World Data

Abhinav Agarwal, Sushant Veer, Allen Z. Ren, Anirudha Majumdar

ICRA 2022poster

We are motivated by the problem of learning policies for robotic systems with rich sensory inputs (e.g., vision) in a manner that allows us to guarantee generalization to environments unseen during training. We provide a framework for providing such generalization guarantees by leveraging a finite d…

Cited by 2 Source ↗Scholar ↗