I am currently a NSF mathematical sciences postdoctoral fellow at UC Berkeley, working with Stuart Russell and Eric Brewer. I recently completed my doctorate in computer science at MIT where I worked with Nicholas Roy, Leslie Pack Kaelbling and Tomas Lozano-Perez. My thesis work focused on decision making under uncertainty. Outside of artificial intelligence, I am interested in using information communication technologies for international development. In the past Bill Thies and I co-ran a reading group on this topic: click here to see the website and sign up for our mailing list for periodic postings.

Refereed Publications

• Provably Efficient Learning with Typed Parametric Models
  E.Brunskill, B. Leffler, L. Li, M. Littman, and N. Roy.
  Journal of Machine Learning Research, 2009
• Evaluating the Accuracy of Data Collection on Mobile Phones: A Study of Forms, SMS, and Voice
  S.Patnaik, E.Brunskill, and W.Thies.
  International Conference on Information and Communication Technologies and Development (ICTD) 2009
• Where to Go: Interpreting Natural Directions Using Global Inference
  Y.Wei, E.Brunskill, T.Kollar and N.Roy.
  International Conference on Robotics and Automation (ICRA) 2009
• How Close is Close Enough? Finding Optimal Policies in PAC-style Reinforcement Learning.
  E. Brunskill
  Abstract NIPS 2008 Workshop on Model Uncertainty and Risk in Reinforcement Learning
• CORL: A Continuous-state Offset-dynamics Reinforcement Learner
  E.Brunskill, B.Leffler, L.Li, M.Littman and N.Roy.
  Uncertainty in Artificial Intelligence 2008 oral presentation.
  Tech report with proofs available here.
• Perceptual switch rates with ambiguous structure-from-motion figures in bipolar disorder.
  K.Krug, E.Brunskill, A.Scarna, G.Goodwin and A.Parker.
  Proceedings of the Royal Society B 2008.
• Continuous-state POMDPs with hybrid dynamics.
  E.Brunskill, L.Kaelbling, T.Lozano-Perez, and N.Roy.
  Proceedings of the International Symposium on Artificial Intelligence and Mathematics (ISAIM) 2008
• A supervised learning approach for collision detection in legged locomotion.
  F.Doshi, E.Brunskill, A.Shkolnik, T.Kollar, K.Rohanimanesh, R.Tedrake, and N.Roy
  International Conference on Intelligent Robots and Systems (IROS) 2007
• Topological mapping using spectral clustering and classification.
  E.Brunskill, T.Kollar and N.Roy
  International Conference on Intelligent Robots and Systems (IROS) 2007
• Continuous state POMDPs for object manipulation tasks.
  E.Brunskill
  Association for the Advancement of Artificial Intelligence (AAAI) 2007 Doctoral Consortium
• Lessons from prototyping a microfinance distance learning tool.
  E.Brunskill and T.Parikh
  CHI workshop on User Centered Design for International Development 2007
• Adaptive state space construction with reinforcement learning for robots.
  E.Brunskill, E.Uchibe, and K.Doya
  poster International Conference on Robotics and Automation (ICRA) 2006
• SLAM using incremental probabilistic PCA and dimensionality reduction.
  E.Brunskill and N.Roy.
  International Conference on Robotics and Automation (ICRA) 2005
• Building peer-to-peer systems with Chord, a distributed lookup service.
  F.Dabek, E.Brunskill, F.Kaashoek, D.Karger, R.Morris, I.Stoica, and H.Balakrishnan.
  in Proceedings of the 8th Workshop on Hot Topics in Operating Systems (HotOS-VIII) 2001

• LittleDog learning locomotion project
  CSAIL research abstract 2006
• Impact of Bipolar Disorder on Ambiguous Structure-from-Motion Percepts
  E.Brunskill, et al.
  Society for Neuroscience Abstract (SFN) 2003

Fall 2006-Spring 2007 I co-organized Machine Learning tea.
Summer 2005 I spent in Okinawa, Japan working with Dr.Kenji Doya at OIST.
Fall 2005 I was a teaching assistant for Techniques in AI.

My e-mail address is my first name at csail dot mit dot edu