• Erik Talvitie
Assistant Professor of Computer Science
Mathematics & Computer Science

Education

Ph.D. in Computer Science, University of Michigan (2010)

M.S. in Computer Science, University of Michigan (2007)

B.A. in Computer Science and Mathematics, Oberlin College (2004)

Research

My primary research interests focus on the core artificial intelligence ambition of creating artifical autonomous agents that can behave flexibly and competently in rich, complex environments. I tend to approach this problem through my background in machine learning, and specifically reinforcement learning. Broadly speaking, then, I focus on the learning problem faced by an agent that is placed in an unknown environment and would like to learn, from its own experience, how to make good decisions (where "good" is defined by some specified reward signal). This raises interesting and challenging questions about how such an agent should represent and maintain knowledge in order to make both learning and planning tractible, even when the world is very complex. Beyond this primary focus, I am also quite broadly interested in machine learning in general as a tool for turning the ever-growing mountain of available data into useful computational artifacts.

Publications

Conference Papers

  • Model Regularization for Stable Sample Rollouts. Erik Talvitie. In 'Proceedings of the Thirtieth Conference on Uncertainty in Artifical Intelligence (UAI),' 2014. (pdf)
  • Skip Context Tree Switching. Marc Bellemare, Joel Veness, Erik Talvitie. In 'Proceedings of the Thirty-First International Conference on Machine Learning (ICML),' 2014. (pdf)
  • Learning Partially Observable Models Using Temporally Abstract Decision Trees. Erik Talvitie. In 'Advances in Neural Information Processing Systems 25 (NIPS),' 2012. (pdf)
  • Maintaining Predictions Over Time Without a Model. Erik Talvitie and Satinder Singh. In 'Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence (IJCAI),' 2009. (pdf)
  • Simple Local Models for Complex Dynamical Systems. Erik Talvitie and Satinder Singh. In 'Advances in Neural Information Processing Systems 21 (NIPS),' 2009. (pdf)
  • Building Incomplete but Accurate Models. Erik Talvitie, Britton Wolfe, and Satinder Singh. Tenth International Symposium on Artificial Intelligence and Mathematics (ISAIM), 2008. (pdf)
  • An Experts Algorithm for Transfer Learning. Erik Talvitie and Satinder Singh. In 'Proceedings of the Twentieth International Joint Conference on Artificial Intelligence (IJCAI),' 2007. (pdf)

Journal Papers

  • Learning to Make Predictions In Partially Observable Environments Without a Generative Model. Erik Talvitie and Satinder Singh. Journal of AI Research, Volume 42 (2011), pages 353-392. (pdf)

Dissertation

  • Simple Partial Models for Complex Dynamical Systems. Erik Talvitie. Ph.D. Thesis, University of Michigan, 2010. (pdf)

Student Collaborations

Combining Learning and Search in Atari 2600 Games

  • George Gallo ('14) (Summer 2012 - Fall 2012, Hackman Scholar and Independent Study)
  • William Tran ('14) (Summer 2012 - Spring 2013, Hackman Scholar and Independent Study)

Course Information

Fall 2014:

  • CPS 111: Computer Science I -- Introduction to Computational Thinking
  • CPS 111 Lab
  • CPS 222: Computer Science III

Spring 2013:

  • CPS 337: Theoretical Foundations of Computer Science

Fall 2012:

  • CPS 275: Advanced Data Structures
  • CPS 370: Machine Learning

Spring 2012:

  • CPS 371: Artificial Intelligence
  • CPS 374: Theoretical Foundations of Computer Science

Fall 2011:

  • CPS 111: Computer Science I -- Introduction to Computational Thinking
  • CPS 111 Lab
  • CPS 275: Advanced Data Structures

Spring 2011:

  • CPS 112: Computer Science II -- Algorithms and Data Structures
  • CPS 274: Theoretical Foundations of Computer Science

Fall 2010:

  • CPS 170: Computer Science I -- Introduction to Computational Thinking
  • CPS 170 Lab