Massachusetts Institute of Technology
Natasha Jaques is a PhD candidate at MIT, focusing on improving deep learning agents by building in forms of affective and social intelligence. Her past work has investigated methods for improving generalization of machine learning models via intrinsic motivation, transfer learning, multi-task learning, and learning from human preferences. She has interned at DeepMind, Google Brain, and was an OpenAI Scholars mentor. She received an honourable mention for best paper at ICML 2019, a best paper award at the NeurIPS ML for Healthcare workshop and was part of the team that received Best Demo at NeurIPS 2016. Her work has been featured in Quartz, the MIT Technology Review, Boston Magazine, and on CBC radio. Natasha earned her Masters degree from the University of British Columbia, and undergraduate degrees in Computer Science and Psychology from the University of Regina.
Social learning is a crucial component of human intelligence, allowing us to rapidly adapt to new scenarios, learn new tasks, and communicate knowledge that can be built on by others. Can the ability of artificial intelligence to learn, adapt, and generalize to new environments be enhanced by mechanisms that allow for social learning? My work proposes novel deep- and reinforcement-learning methods that improve the social and affective capabilities of artificial intelligence (AI), through social learning both from humans and from other AI agents. I show how AI agents can learn from each other in a multi-agent environment, and learn from humans by sensing their social and affective cues. Together, these social learning techniques allow AI agents to flexibly learn from each other and from humans.