Welcome to the Reinforcement Learning Reading Group at Gatsby

We meet Fridays at 2:30 - 3:30 in Gatsby seminar room, 4th floor, Gatsby Unit.

DateSpeakerReadingNotes
28 Nov. 2008Mandana AhmadiSutton et al
14 Nov. 2008Adam SanbornDayan & Daw Cont'd
7 Nov. 2008Adam SanbornDayan & Daw
31 Oct. 2008Kai Krueger

Botvinick et al Cont'd

24 Oct. 2008Kai KruegerBotvinick et al
16 Oct. 2008
8 Oct. 2008Canceled (SAB)
3 Oct. 2008Christoph Kolodziejski
23 Sep. 2008Peter Dayan
Overview of RL from a
neuroscience perspective

17 Sep. 2008

Informal Meeting
12 Sep. 2008Peter DayanOverview of RL from a
neuroscience perspective
Dayan & Niv, 2008
Daw & Doya, 2006
Dayan & Daw
5 Sep. 2008

Deciding on topics

If you would like to join us, send me an email to Mandana(at)gatsby.ucl.ac.uk, and I will add you to

the mailing list.

Back to my homepage

Past Sessions:

The book we read was: 

"Reinforcement Learning: An Introduction," by Sutton and Barto,

available online at http://www.cs.ualberta.ca/~sutton/book/the-book.html

Date

Speaker

Reading

Notes

4 April 2008

Mandana Ahmadi

S&B chapters 1&2

 

11 April 2008

Mandana Ahmadi

S&B chapter 3

 

18 April 2008

Cancelled

Cancelled

 

25 April 2008

Peter Latham

S&B chapter 4

 

2 May 2008

Peter Latham

S&B chapter 4 cont’d

Bellman’s eq’n has a unique solution

9 May 2008

Vinayak Rao

S&B chapter 5

 

16 May 2008

Vinayak Rao

Ulrik Beierholm

S&B chapter 5 cont’d

S&B chapter 6

 

23 May 2008

Ulrik Beierholm

Kai Kruger

S&B chapter 6

S&B chapter 7

 

30 May 2008

Kai Kruger

S&B chapter 7

 

6 June 2008

Cancelled (NIPS)

Cancelled (NIPS)

 

20 June 2008

Kai Kruger

S&B chapter 7

 

11 July 2008

Peter Latham

S&B chapter 8

Proof of  eq’n 8.9

 

18 July 2008

Peter Latham

Proof of  eq’n 8.9 cont’d

 

25 July 2008

Ulrik Beierholm

S&B chapter 8 cont’d

 

1 August 2008

Mandana Ahmadi

S&B chapter 9

 

Back to my homepage