Bhavya Agrawalla

2 accepted papers

2026

What Does Flow-Matching Bring to TD-Learning?

Bhavya Agrawalla, Michal Nauman, Aviral Kumar

ICML 2026poster

Recent work shows that flow-matching networks can be effective for value function estimation in reinforcement learning, but it remains unclear why they work well or whether flow-matching Q-functions differ fundamentally from standard critics. We show that their success is not explained by distributi…

Cited by 0 Source ↗Scholar ↗

2023

DISeR: Designing Imaging Systems with Reinforcement Learning

Tzofi Klinghoffer, Kushagra Tiwary, Nikhil Behari, Bhavya Agrawalla, Ramesh Raskar

ICCV 2023poster

Imaging systems consist of cameras to encode visual information about the world and perception models to interpret this encoding. Cameras contain (1) illumination sources, (2) optical elements, and (3) sensors, while perception models use (4) algorithms. Directly searching over all combinations of t…

Cited by 7 PDF ↗Scholar ↗