Hash: SHA1


I'd like to start some discussion again.

The Title "Better Computer Go Player with Neural Network and Long-term
Prediction" seems to put the focus on Long-term Prediction, but my
Problem is, that I can not find the result from the paper.

My main problem is: darkforest and darkfores1 differ in two parameters:

Training database and long term prediction

("Our first bot darkforest is trained using standard features, 1 step
prediction on KGS dataset. The second bot darkfores1 is trained using
extended features, 3 step prediction on GoGoD dataset.")

And the importance of the dataset has be found by previous CNN papers.

I understand the idea, that long term prediction might lead to a
different optimum (but it should not lead to one with a higher one
step prediction rate: it might result in a stronger player with the
same prediction rate...), and might increase training speed, but hard
facts would be great before spending a GPU month into this :)


Am 23.11.2015 um 09:54 schrieb Rémi Coulom:
> It is darkforest, indeed:
> Title: Better Computer Go Player with Neural Network and Long-term 
> Prediction
> Authors: Yuandong Tian, Yan Zhu
> Abstract: Competing with top human players in the ancient game of
> Go has been a long-term goal of artificial intelligence. Go's high
> branching factor makes traditional search techniques ineffective,
> even on leading-edge hardware, and Go's evaluation function could
> change drastically with one stone change. Recent works [Maddison et
> al. (2015); Clark & Storkey (2015)] show that search is not
> strictly necessary for machine Go players. A pure pattern-matching
> approach, based on a Deep Convolutional Neural Network (DCNN) that
> predicts the next move, can perform as well as Monte Carlo Tree
> Search (MCTS)-based open source Go engines such as Pachi [Baudis &
> Gailly (2012)] if its search budget is limited. We extend this idea
> in our bot named darkforest, which relies on a DCNN designed for
> long-term predictions. Darkforest substantially improves the win
> rate for pattern-matching approaches against MCTS-based approaches,
> even with looser search budgets. Against human players, darkforest
> achieves a stable 1d-2d level on KGS Go Server, estimated from free
> games against human players. This substantially improves the 
> estimated rankings reported in Clark & Storkey (2015), where
> DCNN-based bots are estimated at 4k-5k level based on performance
> against other machine players. Adding MCTS to darkforest creates a
> much stronger player: with only 1000 rollouts, darkforest+MCTS
> beats pure darkforest 90% of the time; with 5000 rollouts, our best
> model plus MCTS beats Pachi with 10,000 rollouts 95.5% of the
> time.
> http://arxiv.org/abs/1511.06410
> Rémi
> On 11/03/2015 08:32 PM, Nick Wedd wrote:
>> I think this Facebook AI may be the program playing on KGS as 
>> darkforest and darkfores1.
>> Nick
>> On 3 November 2015 at 14:28, Petr Baudis <pa...@ucw.cz 
>> <mailto:pa...@ucw.cz>> wrote:
>> Hi!
>> Facebook is working on a Go AI too, now:
>> https://www.facebook.com/Engineering/videos/10153621562717200/ 
>> https://code.facebook.com/posts/1478523512478471
>> http://www.wired.com/2015/11/facebook-is-aiming-its-ai-at-go-the-game-no-computer-can-crack/
The way it's presented triggers my hype alerts, but nevertheless:
>> does anyone know any details about this?  Most interestingly,
>> how strong is it?
>> -- Petr Baudis If you have good ideas, good data and fast
>> computers, you can do almost anything. -- Geoffrey Hinton 
>> _______________________________________________ Computer-go
>> mailing list Computer-go@computer-go.org
>> <mailto:Computer-go@computer-go.org> 
>> http://computer-go.org/mailman/listinfo/computer-go
>> -- Nick Wedd mapr...@gmail.com <mailto:mapr...@gmail.com>
>> _______________________________________________ Computer-go
>> mailing list Computer-go@computer-go.org 
>> http://computer-go.org/mailman/listinfo/computer-go
> _______________________________________________ Computer-go mailing
> list Computer-go@computer-go.org 
> http://computer-go.org/mailman/listinfo/computer-go
Version: GnuPG v2.0.22 (GNU/Linux)

Computer-go mailing list

Reply via email to