[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: current development
From: |
Timothy Y. Chow |
Subject: |
Re: current development |
Date: |
Thu, 5 Dec 2019 11:32:00 -0500 (EST) |
User-agent: |
Alpine 2.21 (LRH 202 2017-01-01) |
On Thu, 5 Dec 2019, Nikos Papachristou wrote:
My personal view on improving GNUBG: Why not try to "upgrade" your
existing supervised learning approach? There have been lots of advances
in optimization/regularization algorithms for neural networks in the
past years and it might be less demanding that trying a new RL self-play
approach from scratch.
Regarding expected results, I also believe that backgammon bots are very
close to perfection and whatever improvements (from any approach) will
be marginal.
In order to determine whether a new network is doing better than the old
network, it helps to have examples of positions where the old network is
clearly playing poorly. Here's one example of a game that I played
against eXtreme Gammon where the bot made a lot of obvious blunders:
http://timothychow.net/cg/Games/7pt2015-05-24e%20Game%202.htm
For example, search for "10/8 6/4(3)". The bot's ridiculous play here
would not be among the top 50 plays of any halfway decent human player.
Admittedly this was XG but I would expect GNU to behave similarly, if not
in these specific positions then in similar ones.
Playing around with positions like this will quickly disabuse anyone of
the illusion that "backgammon bots are very close to perfection."
As I recall, in the past, people have tried specifically training neural
nets on positions like these, as well as "snake" positions where you have
to roll a prime for a long distance, and the problem was that it seemed to
degrade performance on other types of positions. It's possible that, as
Papachristou suggests, recent incremental improvements in regularization
algorithms might be good enough to overcome these difficulties. Anecdotal
evidence from Robert Wachtel's revised version of "In the Game Until the
End" suggests that Xavier was able to improve eXtreme Gammon's post-coup
classique play significantly, without a wholesale switch to modern deep
learning methods.
Tim
- Re: current development, (continued)
- Re: current development, Philippe Michel, 2019/12/04
- Re: current development, Joseph Heled, 2019/12/04
- Re: current development, Joseph Heled, 2019/12/04
- Re: current development, Nikos Papachristou, 2019/12/05
- Re: current development, Øystein Schønning-Johansen, 2019/12/05
- Re: current development, Nikos Papachristou, 2019/12/05
- Re: current development, Joseph Heled, 2019/12/05
- Re: current development, Nikos Papachristou, 2019/12/06
- Re: current development, Joseph Heled, 2019/12/06
- Re: current development, Nikos Papachristou, 2019/12/06
- Re: current development,
Timothy Y. Chow <=
- Re: current development, Nikos Papachristou, 2019/12/07
- Re: current development, Joseph Heled, 2019/12/07
- Re: current development, Timothy Y. Chow, 2019/12/07
- Re: current development, Joseph Heled, 2019/12/07
- Re: current development, Timothy Y. Chow, 2019/12/07
- Re: current development, Joseph Heled, 2019/12/07
- Re: current development, Timothy Y. Chow, 2019/12/07
- Re: current development, Joseph Heled, 2019/12/07
- Re: current development, Timothy Y. Chow, 2019/12/07
- Re: current development, Philippe Michel, 2019/12/08