David Brandfonbrener

New York University

Papers

1

Total Citations

3

H-Index

1

About

David Brandfonbrener is a researcher advancing the frontiers of reinforcement learning and robotics, with a particular focus on data-efficient policy learning from offline and image-based sources. His most cited work, "Visual Backtracking Teleoperation," introduces a novel data collection protocol that strategically guides teleoperators to gather richer, more informative datasets for training robust, image-based value functions and policies in sparse reward robotic tasks. By modifying standard demonstration collection to include corrective and exploratory trajectories, Brandfonbrener’s approach directly addresses the critical bottleneck of data quality in offline RL, enabling more reliable generalization from limited human input. This contribution has garnered early recognition, with 3 citations since its 2023 publication, signaling growing influence in the robotics and machine learning communities. His work sits at the intersection of human-robot interaction, computer vision, and reinforcement learning, offering practical methodologies that reduce the burden on teleoperators while improving downstream policy performance. Brandfonbrener’s research is particularly valuable for students and practitioners seeking to deploy learning-based systems in real-world settings where data is scarce and reward signals are weak.

Research Focus

Key Achievements

1
H-Index
1
Papers
3
Total Citations
3
Avg Citations/Paper
🏆 Most Cited Paper
Visual Backtracking Teleoperation: A Data Collection Protocol for Offline Image-Based Reinforcement Learning
3 citations · 2023
📈 Most Prolific Year: 2023 (1 Papers)
🤝 Key Collaborators: 6
🏛 Institutions: New York University

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago