Hi,

I've recently renewed my interest in backgammon. I am a total noob who enjoys playing against the computer and analyzing my games after that to see where I made mistakes.

I've bought XG as it's supposedly the strongest program out there. I've noticed that the copyright notice says 2009-2013 suggesting the development stopped then. As 2013 is before huge hardware and algorithmic advancement of recent years (especially when it comes to neural networks) it looks to me that there are two possibilities:

1)XG is so close to perfection that any improvements wouldn't make much of a difference

2)XG can be beaten significantly by implementing modern techniques (for starters make it use GPU and use modern big Neural Net akin to those used in chess or go these days)

I have two questions I realize are difficult to answer objectively but I appreciate opinions or at least slightly educated guesswork as well.
My questions are the following:

1)How far do you think XG at reasonable high settings (let's say it can spend 2 seconds per move on modern hardware) is from perfection?

2)Is there any money/recognition/fun to gain from developing a stronger engine?

The reason I am asking this is that I am interested in Neural Network based engines. Chess (my main game) is very far advanced now and a difficult ground to contribute meaningfully. Backgammon software looks like much easier target.

Q1: No way to really tell but it's substantially better than the best human players.

Q2: Money? This would depend more on how good your interface is rather than on the playing strength of the program. XG's interface is excellent.

Recognition? Nearly zero here I would guess.

Fun? Only you can answer that.

I was hoping that maybe strong backgammon players have an intuition about it.
In chess for example we felt the engines are far away from perfect because we understood type of positions they get wrong on regular basis. This was more than a decade after engines already have beaten best human players. It's changing these days with NN based engines. More people are in "chess is softly solved" camp (given strong hardware and a lot of time, for example 1 hour per move).

Yeah I like XG interface. I am just interested in the engine itself.
I have heard complaints that backgammon for money online died because it's too easy to run into bots. The thing is that if I have a stronger engine I would love to run into bots and give them unlimited action.

there's no way in hell to make a game engine strong enough to overcome another bot + rake

It's hard to say. XG rates itself an 0.15 error rating which is pretty good. If you accept that a bot rating its own play has some issues you might add another 0.2-0.4. Just an educated guess. I recently analysed some dozens matches of another bot against itself with XG and that showed that perfection is not yet reached.


This one is easy to answer. If you look at chess and Go they are 2D. Here the image recognitions algorithms shine (i.e. convolutional nets). Backgammon is in essence 1D and therefore the "classical" approach having a Multilayer Perceptron with one hidden layer works extremely well (for GnuBG, TD_Gammon and BGBlitz I'm sure about that architecture. XG, Sowie and Jellyfish most probably do the same)

One issue with the GPU is that it takes quite some time to move the data to the GPU. In fact you've calculate it on the CPU much quicker. I recently found a website where training of Backgammon AI was made on a GPU. 1000 games in an hour. Impressive? On a single CPU core, with the perceived slow language Java on a recent laptop I need for 1000 games about 30 seconds...
Don't get me wrong GPUs are fantastic technology, but the problem must fit.
(A bit more technical: MLP is Level 2 Blas where memory access dominates computation nowadays. Convolutional nets are Blas level 3 where you could reuse an item quite a lot, so calculation dominates memory access and GPUs outperform CPUs)


see above, maybe PR 0.4. It might be that e.g. backgames with new strategies turn game play around (comparable to what AlphaZero did to Stockfish, where it played much different than we are used to), but I won't bet on that. And I'm confident that no one can judge that.

fun definitely yes.

Money/recognition only if you surpass XG in some critical features (e.g. XG is really fast. Much faster than the competition).

About 25 years ago I asked myself whether writing a chess engine or an BG engine should be my next spare time project. I judged that chess will probably need 2-3 years to get something competitive, so I decided for Backgammon being quicker to get something reasonable . Boy was I off....