[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
RE: [Bug-gnubg] Neurogammon by Tesauro
From: |
Alain Redlinger |
Subject: |
RE: [Bug-gnubg] Neurogammon by Tesauro |
Date: |
Mon, 22 Jun 2009 15:43:32 +0200 |
Hi Ian
Have you got a copy of this one ?
Gerald Tesauro
Programming backgammon using self-teaching neural nets
Artificial Intelligence 134 (2002) 181-199
Regards,
Alain
> -----Original Message-----
> From: address@hidden
> [mailto:address@hidden
> On Behalf Of Alain Redlinger
> Sent: 19 June 2009 16:01
> To: 'bug-gnubg'
> Subject: RE: [Bug-gnubg] Neurogammon by Tesauro
>
>
> Hi Ian,
> I do not have the papers you mention, but you might have a
> look at these:
>
> http://www.research.ibm.com/massive/tdl.html#h1:temporal_diffe
> rence_learning
>
> http://satirist.org/learn-game/systems/gammon/
>
> best regards,
> Alain
Thanks Alain. I'm already aware of these pages. Unfortunately, Tesauro
doesn't go into the details of Neurogammon here; he just refers the
reader to the papers I cited.
-- Ian