Intelligent biological agents generate actions to explore the world actively.  Artificially intelligent agents today attempt to mimic them, but they fall significantly behind in terms of efficiency, effectiveness, and reliability. The Active Generative Agents (AGA) Lab at the UNIST Graduate School of AI aims to investigate the principles underlying intelligence and apply them to build intelligent systems that can interact with the world actively, efficiently, and safely. 

AGA Lab is primarily interested in developing principled methods at the intersection of generative modeling and reinforcement learning. We apply our algorithms to various high-impact real-world applications, including, but not limited to, robotics foundation models, biochemistry, particle physics, chemical engineering, and adtech.