Alane Suhr - Training Language-Conditioned Agents with Reinforcement Learning

Title: Training Language-Conditioned Agents with Reinforcement Learning

Bio: Alane Suhr is an Assistant Professor in the Department of Electrical Engineering and Computer Sciences at UC Berkeley. Alane received a PhD in Computer Science from Cornell University in 2022, and afterwards spent a year at the Allen Institute for AI (AI2) in Seattle as a Young Investigator on the Mosaic team. Alane holds a BS in Computer Science and Engineering with a minor in Linguistics from Ohio State University. Alane's research lies at the intersection of natural language processing, machine learning, and computer vision. Alane focuses on building systems that use language to interact with people, such as in collaborative settings (e.g., CerealBar), and designs models and datasets that tackle problems in language grounding (e.g., NLVR) and develops learning algorithms that enable systems to acquire language through interaction.