Emma Brunskill

Assistant Professor
Computer Science Department
Carnegie Mellon University
ebrunskill at cs dot cmu dot edu

My research interests include machine learning, sequential decision making under uncertainty, and artificial intelligence. I am particularly interested in using these approaches to transform the quality of education. I am also interested in using information and communication technologies for international development and health applications.

Please see a fairly recent cv for more information on me and my work. I did my PhD at MIT and my postdoc at the University of California, Berkeley. At CMU I am also affiliated with the Machine Learning Department.

News

• Summer 2013: Yun-en Liu's EDM paper is nominated for best paper. Congratulations Yun-en!
• Summer 2013: Paper with Mohammad Azer and Alessandro Lazaric on ("Regret Bounds for Reinforcement Learning with Policy Advice") accepted to ECML
• Spring 2013: Paper with Lihong Li on multi-task reinforcement learning accepted to UAI
• Spring 2013: Two papers accepted to Education Data Mining. Congratulations to Yun-en Liu and Anna Rafferty!
• Dec 2012: I gave a joint invited tutorial with Geoff Gordon on "Machine Learning for Student Learning" at NIPS.
• Fall 2012: I had a great time presenting my group's work as part of CMU's IdeasLab at the World Economic Forum in Tianjin, China.
• Summer 2012: I received a Google Research Award. Thanks Google!
• Summer 2012: Paper on Incentive Decision Processes (with Sashank Reddi) accepted to UAI.
• Summer 2012: Jung In Lee and I had a paper nominated for best paper at the International Conference on Educational Data Mining. Congratulations to Jung In!
• Spring 2012: I'm delighted to have been selected as a Microsoft Research Faculty Fellow.
• Spring 2012: I co-taught (with Professor Manuela Veloso) a new class on Artificial Intelligence for Health & Sustainability.
• Summer 2011: I co-organized a IJCAI workshop on Decision Making in Partially Observable, Uncertain Worlds

Selected Publications (Full list available here)

• RAPID: A reachable anytime planner for imprecisely-sensed domains [pdf]
  E.Brunskill and S.Russell
  Uncertainty in Artificial Intelligence (UAI) 2010
• Provably efficient learning with typed parametric models [pdf]
  E.Brunskill, B. Leffler, L. Li, M. Littman, and N. Roy.
  Journal of Machine Learning Research, 2009
• Evaluating an adaptive multi-user educational tool for low-resource regions [pdf]
  E.Brunskill, S.Garg, C.Tseng, J.Pal and L.Findlater
  International Conference on Information and Communication Technologies and Development (ICTD) 2010