Rich Sutton's Home Page

Richard S. Sutton

Professor and iCORE chair
Department of Computing Science
University of Alberta
2-21 Athabasca Hall
Edmonton, Alberta
Canada T6G 2E8

office 3-13 Athabasca Hall 780-492-4584
cell 780-270-8139 fax 780-492-1111
email sutton@cs.ualberta.ca or rich@richsutton.com
web http://richsutton.com aka http://www.cs.ualberta.ca/~sutton
buddy/aol name rssutton@mac.com (do not use this for an email address)

Research

Brief biography
Publications
Talks
Reinforcement Learning: An Introduction (textbook)
RL FAQ - Frequently asked questions about reinforcement learning
my schedule/calendar
Photos, older photos
CMPUT 609 - Reinforcement Learning for Artificial Intelligence (Winter 2009)
CMPUT 325 - Non-procedural Programming Languages (Fall 2006)
CMPUT 607 - Reinforcement Learning in Practice (Winter 2005)
CMPUT 366 - Intelligent Systems (Introduction to AI)
Incomplete Ideas
- What's Wrong with AI 11/12/01
- Verification, The Key to AI 11/15/01
- Verification 11/14/01
- Mind is About Information 11/19/01
- Mind is About Predictions 3/21/00
- Subjective Knowledge 4/6/01
Software
- See rlai.net for updated versions of some of the below plus
- Tile Coding Software: Version 1. Version 2.0.
- RandomMDPs.lisp, for learning and planning with tabular or factored MDPs
- G, a graphics package for Macintosh Common Lisp
- A simple graphing tool for Macintosh Common Lisp
- More...
Favorite causes: IJ, Downsize DC, Technoserve, DPF, Vote Smart, CATO, AntiWar, Ron Paul, Not in Our Name
Ron Paul for President, wouldn't that be wonderful
Political ideas

I am seeking to identify general computational principles underlying what we mean by intelligence and goal-directed behavior. I start with the interaction between the intelligent agent and its environment. Goals, choices, and sources of information are all defined in terms of this interaction. In some sense it is the only thing that is real, and from it all our sense of the world is created. How is this done? How can interaction lead to better behavior, better perception, better models of the world? What are the computational issues in doing this efficiently and in realtime? These are the sort of questions that I ask in trying to understand what it means to be intelligent, to predict and influence the world, to learn, perceive, act, and think.