Anca Dragan

Anca Dragan is an Associate Professor in the Department of Computer Science at the University of California, Berkeley. Her research focuses on Artificial Intelligence (AI), Control, Intelligent Systems, and Robotics (CIR), as well as Human-Computer Interaction (HCI). Dragan leads the InterACT lab, which explores AI alignment, human-AI collaboration, and algorithms for assisting humans in physical and virtual tasks. Her work involves enabling AI agents and robots to interact effectively with people by learning from human feedback and modeling decision-making. Dragan is affiliated with several research centers, including the Berkeley Artificial Intelligence Research Lab (BAIR) and the Center for Human Compatible Artificial Intelligence (CHAI).

Anca D Dragan is an Assistant Professor at UC Berkeley and Director of AI Safety and Alignment at Google DeepMind. Her research focuses on AI Alignment, Human-AI Collaboration, Robotics, and Machine Learning. Dragan's work explores the challenges of aligning AI systems with human values, improving human-robot interaction, and developing robust control strategies for autonomous systems. Her publications address topics such as cooperative inverse reinforcement learning, legibility of robot motion, and the impact of robot behavior on human collaboration. She also investigates the theoretical and practical limitations of reinforcement learning from human feedback and the development of safe, interpretable AI systems.