Regular biography
Benjamin Eysenbach is an Assistant Professor in the Department of Computer Science at Princeton University. He joined the Princeton faculty in 2023 after completing a Ph.D. in machine learning at Carnegie Mellon University. His research focuses on developing principled reinforcement learning algorithms that achieve state-of-the-art performance with greater simplicity, scalability, and robustness. Much of his work leverages probabilistic inference to address challenges in reinforcement learning, such as long-horizon and high-dimensional reasoning, robustness, and exploration. He has an undergraduate degree in mathematics from MIT and has spent time at Google Brain/Research during his doctoral studies.
Scholar-generated biography
Benjamin Eysenbach is a researcher at Princeton University specializing in reinforcement learning. His work explores methods to enhance learning efficiency and safety in autonomous systems. He focuses on developing techniques that enable agents to learn from limited or unstructured data, such as through offline reinforcement learning, unsupervised learning, and goal-conditioned tasks. His research also addresses challenges in exploration, safety, and transfer learning, aiming to improve the robustness and generalization of reinforcement learning algorithms. Eysenbach's contributions span both theoretical and applied aspects of reinforcement learning, with an emphasis on practical deployment in real-world environments.