Benjamin Eysenbach

Benjamin Eysenbach is an Assistant Professor in the Department of Computer Science at Princeton University's School of Engineering and Applied Science since 2023. His research focuses on developing principled reinforcement learning (RL) algorithms that improve simplicity, scalability, and robustness in state-of-the-art systems, particularly through probabilistic inference techniques.

• Ph.D., Machine Learning, Carnegie Mellon University (2023)
• B.S., Mathematics, Massachusetts Institute of Technology

Research interests center on reinforcement learning with emphasis on long-horizon reasoning, exploration strategies, and robustness. He explores intersections with probabilistic inference and self-supervised learning to enhance RL capabilities.

Recent publications highlight trends in contrastive learning for goal-conditioned RL, temporal distance modeling, and hierarchical control. Key themes include reward-free learning, scalable architectures, and uncertainty quantification in decision-making systems.

• 2025: Junior Faculty Award for Excellence in Research and Teaching, Princeton School of Engineering and Applied Science

Eysenbach's work bridges theoretical foundations with practical implementations in AI training frameworks, emphasizing performance optimization and safety mechanisms.