Chelsea Finn researches the capability of robots and other agents to develop broadly intelligent behavior through learning and interaction.
To this end, she has developed deep learning algorithms for concurrently learning visual perception and control in robotic manipulation skills, inverse reinforcement methods for scalable acquisition of nonlinear reward functions, and meta-learning algorithms that can enable fast, few-shot adaptation in both visual perception and deep reinforcement learning.
Throughout her career, she has sought to increase the representation of underrepresented minorities within computer science and artificial intelligence by developing an AI outreach camp at Berkeley for underprivileged high school students, and a mentoring program for underrepresented undergraduates across three universities. She also leads efforts within the WiML and Berkeley WiCSE communities of women researchers.
ACM Doctoral Dissertation Award
MIT Technology Review 35 under 35 Award
C.V. Ramamoorthy Distinguished Research Award
NSF Graduate Fellowship