If you need assistance, please send an email to forum at 4hv dot org. To ensure your email is not marked as spam, please include the phrase "4hv help" in the subject line. You can also find assistance via IRC, at irc.shadowworld.net, room #hvcomm.
Support 4hv.org!
Donate:
4hv.org is hosted on a dedicated server. Unfortunately, this server costs and we rely on the help of site members to keep 4hv.org running. Please consider donating. We will place your name on the thanks list and you'll be helping to keep 4hv.org alive and free for everyone. Members whose names appear in red bold have donated recently. Green bold denotes those who have recently donated to keep the server carbon neutral.
Special Thanks To:
Aaron Holmes
Aaron Wheeler
Adam Horden
Alan Scrimgeour
Andre
Andrew Haynes
Anonymous000
asabase
Austin Weil
barney
Barry
Bert Hickman
Bill Kukowski
Blitzorn
Brandon Paradelas
Bruce Bowling
BubeeMike
Byong Park
Cesiumsponge
Chris F.
Chris Hooper
Corey Worthington
Derek Woodroffe
Dalus
Dan Strother
Daniel Davis
Daniel Uhrenholt
datasheetarchive
Dave Billington
Dave Marshall
David F.
Dennis Rogers
drelectrix
Dr. John Gudenas
Dr. Spark
E.TexasTesla
eastvoltresearch
Eirik Taylor
Erik Dyakov
Erlend^SE
Finn Hammer
Firebug24k
GalliumMan
Gary Peterson
George Slade
GhostNull
Gordon Mcknight
Graham Armitage
Grant
GreySoul
Henry H
IamSmooth
In memory of Leo Powning
Jacob Cash
James Howells
James Pawson
Jeff Greenfield
Jeff Thomas
Jesse Frost
Jim Mitchell
jlr134
Joe Mastroianni
John Forcina
John Oberg
John Willcutt
Jon Newcomb
klugesmith
Leslie Wright
Lutz Hoffman
Mads Barnkob
Martin King
Mats Karlsson
Matt Gibson
Matthew Guidry
mbd
Michael D'Angelo
Mikkel
mileswaldron
mister_rf
Neil Foster
Nick de Smith
Nick Soroka
nicklenorp
Nik
Norman Stanley
Patrick Coleman
Paul Brodie
Paul Jordan
Paul Montgomery
Ped
Peter Krogen
Peter Terren
PhilGood
Richard Feldman
Robert Bush
Royce Bailey
Scott Fusare
Scott Newman
smiffy
Stella
Steven Busic
Steve Conner
Steve Jones
Steve Ward
Sulaiman
Thomas Coyle
Thomas A. Wallace
Thomas W
Timo
Torch
Ulf Jonsson
vasil
Vaxian
vladi mazzilli
wastehl
Weston
William Kim
William N.
William Stehl
Wesley Venis
The aforementioned have contributed financially to the continuing triumph of 4hv.org. They are deserving of my most heartfelt thanks.
Registered Member #1062
Joined: Tue Oct 16 2007, 02:01AM
Location:
Posts: 1529
For a project, i am attempting to make a program to 'learn'. To start of with, i made 2 tic-tac-toe programs. 1 goes randomly, and 1 picks "winning" spots more frequently. The 2 programs are here: The first one is with learning, 2nd one with random. The mini ttt board on the learning one shows the ranges, ranges get bigger as spot is used more(winning). The 2nd one shows wins when somone wins as a coordinate (X,O).
Can you guys play a few games and tell me if the "learning" one is any better? The learning one is simply randomly choosing, but based on the range, more of a chance of being accepted. The random one has 1/10th of a chance of being accepted, and keeps going until a move is accepted.
The random will be a bit flickery, but its fine, i just made that one constantly repaint (it wont erase when taken off screen for a moment like the random one).
Tell me what you guys think.
Forgot to mention, you click the square to go there, sometimes you may have to click twice.
EDIT: I added a new one. This has a different way of deciding where to go. Each square has a rank 1-10 (look on mini board) starting on five. If its winning square it goes up (2 wins). It then goes to the highest rank square, and gets rank*10 times to try and get 2 random numbers (1-3) matching up with the square position (upper right is 1,1).
Registered Member #1262
Joined: Fri Jan 25 2008, 05:22AM
Location: Maryland, USA
Posts: 451
Yeah, the top one. I just played it more and went 17 and 3. Of course I think its because the learning is somewhat predictable, where as the random one does weird stuff and is hard to anticipate.
Registered Member #540
Joined: Mon Feb 19 2007, 07:49PM
Location: MIT
Posts: 969
hmm I think there is a bug in the random one because sometimes when it is o o _ x x _ o _ x and I move o o _ x x x o _ x
it adds a winning count to the comp's score. Also, I think that if the last move were to be a winning move for me, it doesn't count it. For some reason though, it doesn't seem to be the case all the time. I donno though...
Registered Member #1062
Joined: Tue Oct 16 2007, 02:01AM
Location:
Posts: 1529
aonomus, thats what i do. For the 2nd one, it chooses randomly, but has a certain chance that its accepted. Succeessfull positions have moreof a chance.
The 1st one takes the highest ranked position, and uses Math.random to get to x,y coords. It gets 10*rank tries to get the random X,Y to the coords its on now, and it works its way down the ladder.
Yep, they are buggy, sometimes it gives you a free win, sometimes O a free win, but i cant figure out why =p. I did some more research and i found that Tic-Tac-Toe is a really bad game to try out neural networks because
1) such a limited playing board nothing to 'learn' 2) If playing the simple optimal strategy, its impossible to loose
Myke: It does add the winning move, but its gotta win twice to go up 1 rank, because it does Math.round((max[x][y] - min [x][y])/10), so the rounding makes it not 1 every time.
Rather than try Connect 4 next, i am going to try planning out and making one for GO. This one will have to be mor efficient coding. My tic tac toe program is ~ 1,000 lines of code (with alot of commenting) so its difficult to debug.
This site is powered by e107, which is released under the GNU GPL License. All work on this site, except where otherwise noted, is licensed under a Creative Commons Attribution-ShareAlike 2.5 License. By submitting any information to this site, you agree that anything submitted will be so licensed. Please read our Disclaimer and Policies page for information on your rights and responsibilities regarding this site.
Tic-Tac-Toe :: Learning
