Author |
Topic: Article on neural-net poker AI (Read 3371 times) |
|
dht
Forum Full Member
Arimaa player #8821
Gender: 
Posts: 25
|
 |
http://www.bkgm.Re: Article on neural-net poker AI
« Reply #1 on: Oct 28th, 2013, 7:50am » |
 Quote  Modify
|
Quote:He started with backgammon, though. While a student at the University of Oslo, where he concentrated on computer science, he developed a penchant for the game. He once made it to the finals of the Norwegian National Backgammon Championships. “One thing I learned from backgammon is how to handle losses, no matter how well I play,” he says. “It is not a good game for sore losers.”
Rather than be sore, he used computers to improve his play. Dahl created a neural net that predicted the probability of winning a backgammon match from each position on the board, at every possible stage in a game. Any individual situation is easy enough to solve, Dahl says; the challenge was determining all possible situations, giving value to the importance of each one and choosing a play. “The program needed to self-train and discover these strategies itself,” Dahl says. |
|
That's jellyfish... I think it uses TD-Lambda? 
http://www.edcollins.com/backgammon/technology.htm <--- Background
http://www.bkgm.com/articles/page07.html <--- Lots of useful stuff here
The daddy of all neural network backgammon playing things was TD-Gammon
http://www.scholarpedia.org/article/User:Gerald_Tesauro/Proposed/Td-gamm on
http://www.bkgm.com/articles/tesauro/tdl.html
And random links of ancient stuff since I'm link dumping anyway
http://www.bkgm.com/articles/Berliner/BackgammonProgramBeatsWorldChamp/i ndex.html <--- From 1980
http://minnie.tuhs.org/cgi-bin/utree.pl?file=4.4BSD/usr/src/games/chess
|
|
 IP Logged |
|
|
|
|
Home
Help
Search
Members
Login
Register
Reply
Notify of replies
Send Topic
Print