AI Agents That Do What We Want: Progress and Open Challenges

Researchers used to define objectives for artificial intelligence (AI) agents by hand, but with progress in optimization and reinforcement learning, it became obvious that it’s too difficult to think of everything ahead of time and write it down. Instead, these days the objective is viewed as a hidden part of the state on which researchers can receive feedback or observations from humans - how they act and react, how they compare options, what they say. In this talk, Dragan will discuss what this transition has achieved, what open challenges researchers still face and ideas for mitigating them. This lecture will go over applications in robotics and how the lessons there apply to virtual agents like large language models.

Attend in person or register to attend online

Speaker: Anca Dragan, UC Berkeley