People at CTMS

» Search People

Ronald Parr, Professor of Computer Science and Faculty Network Member of The Energy Initiative

 

Ronald Parr

Features of web page have been intentionally disabled by Ron Parr. Please visit Ron Parr's personal web page for up-to-date information.

Contact Info:
Office Location:  D209 Lev Sci Res Ctr, Durham, NC 27708
Office Phone:  (919) 660-6537
Email Address: send me a message
Web Page:  http://www.cs.duke.edu/~parr

Teaching (Fall 2017):

  • COMPSCI 590.02, ADVANCED TOPICS IN CPS Synopsis
    Gross Hall 104, TuTh 01:25 PM-02:40 PM
Teaching (Spring 2018):
  • COMPSCI 270.01, INTRO TO AI Synopsis
    LSRC B101, TuTh 04:40 PM-05:55 PM

Education:

Doctor of PhilosophyUniversity of California, Berkeley1998
Artium Baccalaureus (cum laude)Princeton University1990

Research Interests:

Methods for solving large stochastic planning problems (MDPs): dynamic programming, reinforcement learning, and policy search. I am interested in techniques for decomposing large problems using hierarchy, problem structure and prior knowledge. I also am interested in Bayesian networks, tracking, learning, probabilistic robotics and, generally, most forms of reasoning under uncertainty.

Areas of Interest:

AI
Robotics
MDPs
Reinforcement Learning
Bayesian Networks

Keywords:

AI • Robotics • MDPs • Reinforcement Learning • Bayesian Networks

Recent Publications   (More Publications)

  1. Pazis, J; Parr, R, Efficient PAC-optimal exploration in concurrent, continuous state MDPs with delayed updates, 30th AAAI Conference on Artificial Intelligence, AAAI 2016 (January, 2016), pp. 1977-1985, ISBN 9781577357605  [abs]
  2. Burchfiel, B; Tomasi, C; Parr, R, Distance minimization for reward learning from scored trajectories, 30th AAAI Conference on Artificial Intelligence, AAAI 2016 (January, 2016), pp. 3330-3336, ISBN 9781577357605  [abs]
  3. Song, Z; Parr, R; Liao, X; Carin, L, Linear feature encoding for reinforcement learning, Advances in Neural Information Processing Systems (January, 2016), pp. 4231-4239  [abs]
  4. Pazis, J; Parr, R; How, JP, Improving PAC exploration using the median of means, Advances in Neural Information Processing Systems (January, 2016), pp. 3898-3906  [abs]
  5. Mason, J; Marthi, B; Parr, R, Unsupervised discovery of object classes with a mobile robot, Proceedings - IEEE International Conference on Robotics and Automation (January, 2014), pp. 3074-3081, ISSN 1050-4729 [doi]  [abs]