Reinforcement Learning and Artificial Intelligence (RLAI)

RLAI-group meeting and mailing list 

Edited by David Silver --David Silver, Oct 2005

This page was retired in May 2006, replaced by the tea-time meetings page.

The RLAI group at the University of Alberta meets each Wednesday from 2:00-3:00pm in CSC 333. Each week we either discuss a relevant paper on RL, or someone will present  current work or ideas.

The ambition of this web page is to:

    1. Announce upcoming papers and presentations
    2. Provide links to the papers under discussion
    3. Keep a record of past papers and presentations
    4. Hold an ongoing discussion of possible possible future papers

Please add your suggestions for future papers by extending this page.

This page also serves as the RLAI group's mailing list.  You can subscribe to or send to the list.

UofA RLAI home, earlier group mtgs

Papers and presentations

Date
 Topic
 Papers
 Presenter / Discussion leader
Jan 18
 Benchmarking in Reinforcement Learning
 abstract
 Adam White
Jan 25
 Benchmarking in Reinforcement Learning (continued)
Adam White
Feb 1
 Steps Toward Artificial Intelligence
 minsky61
 Rich Sutton
Feb 8
 Steps Toward Artificial Intelligence (continued)

Feb 15
 On-Line Algorithms in Machine Learning (a survey)
 blum96
 Martin Zinkevich
Feb 22
 No meeting (AAAI deadline)

Mar 1
 Pandemonium: A paradigm for learning selfridge
Mar 8
 iLSTD: Incremental Least-Square TD
 ilstd06 Alborz Geramifard
Mar 15
 Adaptive TD and other half-baked ideas
David Silver
Mar 22
 Reinforcement Learning in Continuous Time and Space
 doya00
Mar 29 The symbol grounding problem (Harnad)
 harnad90
 Anna? Brian? Rich?
Apr 26
 Pascal Poupart


Papers and presentations from 2005


Invitation for future papers and presentations

If you have an idea for a paper or presentation, please email silver@cs.ualberta.ca or select "Extend this page" and add your idea. All suggestions are welcome; any topics relevant to RL research will be considered.

eyes on the prize (Nilsson, AI magazine)
reasoning in rats (Tolman and Honzig)  
Intelligence without representation, Rodney Brooks  
Artificial intelligence meets natural stupidity, by Drew McDermott  
i think we should do this animal learning theory paper.  Looks very interesting, and it is by Jim Kehoe, who will visit us in the fall.  
the stranger, by mark twain.  --rich, tu Mar 1 2006
next weeks rlai paper:
The symbol grounding problem (Harnad, 1990)
disc leader: Anna? Brian? Rich?  
there will be no RLAI group meeting this week or next.  the next meeting will be on april 26 and will feature Pascal Poupart from Waterloo. -rs
i believe this week's rlai meeting will be at noon (wednesday), perhaps in csc-333 and featuring Pascal Poupart.