RLAI Reinforcement Learning and Artificial Intelligence (RLAI)

Animal Learning Theory Reading Group


This page serves as the organizational nexus for the Animal Learning Theory Reading Group. The goal of this reading group is to mine the literature of animal learning theory for ideas and inspiration for AI. We will start with a classic paper in the field from 1972 by Rescorla & Wagner that describes the eponymous Rescorla-Wagner model. Readings for future weeks will cover different topics, based on the interests of the group.

All meetings will take place in room CSC 2-49.

This page is self-organizing. Those of you who know how, feel free to edit and modify at will. If you don't know how, ask someone that does.

Date
 Time
 Topic
 Link
October 25, 2006
 2 PM
 Organizational + Rescorla-Wagner Model (1972)
 PDF
November 1, 2006
 2 PM Limits of RW Model + Pearce-Hall (1980)
 PDF + Bonus Read
November 8, 2006
 2 PM
 Pearce-Hall (1980) continued...
 See above.
November 15, 2006
 2 PM Discussion: Attention Models + Reinforcement Learning
 See above.
November 22, 2006
Cancelled
November 29, 2006
 2 PM Incentive Learning & the Amygdala
 PDF
December 6, 2006
No Meeting: NIPS
Dec. 13-Jan. 3, 2007
No Meetings: Winter Break
January 10, 2006 2 PM The SOP Model PDF + SOP on Timing
January 17, 2007
 2 PM
 A Real-time Conditioning Model: Sutton & Barto (1981, 1990) Link + Supp. PDF
Jan. 24-Feb. 7, 2007
No Meetings: Conference Deadlines & WCALB
February 14, 2007
 2 PM
 Learning without Association: Gallistel & Gibbon (2000)
 PDF
February 21, 2007
No Meeting: Reading week
February 28, 2007
 2 PM
 Rate Estimation Theory (RET): More Gallistel & Gibbon (2000)
 See above.
March 5, 2007
 2 PM
 Kalman Filters and Acquisition: Kakade & Dayan (2002)
 PDF
March 12-April 11, 2007
No Meetings
April 18, 2007
 2 PM
 TD Learning and Dopamine: Early Story
 PDF + Bonus Read
April 25, 2007
 2 PM
 A TD model of Dopamine Timing: Daw, Courville, & Touretsky (2006) PDF
May 2, 2007
 2 PM
 Another TD-DA Piece. Suri & Schultz (1999).
 PDF
May 9, 2007
 2 PM
 PVLV Model: O'Reilly et al. (2007).
 PDF
May 16, 2007
 2 PM
 Object Recognition in Animals: Spetch & Friedman (2006)
 PDF
May 23-30, 2007
No Meetings
June 6, 2007
 2 PM
 NIPS submissions (in room CSC 328)
 Check email
June 13, 2007
 2:45 PM
 High-level review of Animal Learning Theories: Vogel et al. (2004)
 PDF + Bonus Read
June 20, 2007
No Meeting: Elliot has a baby
June 27, 2007
 2 PM
 Generalization and conditioning: Pearce (1987)
 PDF 
July 4, 2007
 2 PM
 Generalization and conditioning II: Pearce (1994)
 PDF
July 11, 2007
 2 PM
 Are operant and classical conditioning really different?
 Chapter + Article
July 18, 2007
 2 PM
 Innateness of matching: Gallistel et al. (2007)
 PDF
July 25, 2007
 2 PM
 TBA


Note: May 30 and June 6 meetings will need to be in CSC 328.

Some potential topics for future discussion:

More conditioning theories (comparator theories)
Spatial Learning and the Cognitive Map
Timing and Time Perception
Choice
Configural Associations
Generalization and Discrimination
Evolution of Learning (Functional Accounts, Baldwin Effect)
Conditioning and Causation
What is reinforcement/reward?
Some more classics: Skinner, Hull, Hebb, Tolman, Pavlov, Thorndike...
Reasoning
Animal Consciousness
Hyperbolic vs. Exponential Discounting

Extend this Page   How to edit   Style   Subscribe   Notify   Suggest   Help   This open web page hosted at the University of Alberta.   Terms of use  2030/0