There was one program (Shrike) that had a dnn without search. It didn’t finish
in the top 8. Zen and Crazystone have custom DNN implementations. Dark Forest
uses Torch. The rest used Caffe.
Remi's implementation is unusual and interesting. I'll let him share it if he
wants to.
David
> --
Why did darkforest resign? I think darkforest shoud be able to win by about
4 points if it keeps playing.
On Tue, Mar 22, 2016 at 11:55 PM, Hiroshi Yamashita
wrote:
> Hi,
>
> darkforest lost against Koichi Kobayashi with 3 handicaps.
> Next game, Zen vs Kobayashi will be played also with 3 hand
See below:
On Tue, Mar 22, 2016 at 5:21 PM, Lukas van de Wiel <
lukas.drinkt.t...@gmail.com> wrote:
> It would reduce Alphago, because there is less training material in the
> form of high-dan-games, to train the policy network.
>
Maybe not a concern. There has been a suggestion that AlphaGo be
On 22 March 2016 at 21:43, Darren Cook wrote:
< snip >
>
> C'mon DeepMind, put that same version on KGS, set to only play 9p
> players, with the same time controls, and let's get 40 games to give it
> a proper ranking. (If 5 games against Lee Sedol are useful, 40 games
> against a range of playe
On 23.03.2016 15:32, Petr Baudis wrote:
these are beautiful posts.
https://massgoblog.wordpress.com/2016/03/11/lee-sedols-strategy-and-alphagos-weakness/
Before you become too excited, also read my comments on the commentary:
http://www.lifein19x19.com/forum/viewtopic.php?p=200539#p200539
--
Thank you, these are beautiful posts. I enjoyed very much reading
a writeup by Go professional who also took the effort to understand the
principles behind MCTS programs as well as develop a basic intution of
the gameplay artifacts, strengths and weaknesses of MCTS. It also
nicely describes the
Very interesting games!
My feeling is that darkforest rely too much on playing good shape,
and followed Kobayashis light moves too passively on the board.
Maybe it needs a better monte carlo evaluation (does it even have any?).
Zen on the other hand took every opportunity to attack white wildly
David Fotland wrote:
> There are 12 programs here that have deep neural nets. 2 were not
> qualified for the second day, and six of them made the final 8. Many
> Faces has very basic DNN support, but it’s turned off because it
> isn’t making the program stronger yet. Only Dolburam and Many Faces
Wow, Black still recovered after a joseki mistake. You'd expect joseki
to come baked-in, but it didn't need them! I wonder what would happen in
a two stone game.
On 2016-03-23 1:42, Hiroshi Yamashita wrote:
Zen won against KOBAYASHI with 3 handicaps.
(;GM[1]SZ[19]
PB[Zen]
PW[KOBAYASHI Koichi]
Zen won against KOBAYASHI with 3 handicaps.
(;GM[1]SZ[19]
PB[Zen]
PW[KOBAYASHI Koichi]
DT[2016-03-23]
RE[B+4.5]HA[3]KM[0.5]TM[1800]RU[Japanese]
AB[pd][dp][pp]
;W[de];B[dc];W[cc];B[cb];W[cd];B[gc];W[cn];B[fq];W[cj];B[pj]
;W[nc];B[lc];W[qc];B[qd];W[pc];B[od];W[nd];B[oc];W[ob];B[ne]
;W[me];B[pb];W[m
Dear Hiroshi,
many thanks for keeping us informed!
Ingo.
> Gesendet: Mittwoch, 23. März 2016 um 08:06 Uhr
> Von: "Hiroshi Yamashita"
> An: computer-go@computer-go.org
> Betreff: Re: [Computer-go] Densei-sen
>
> SGF is here.
>
> (;GM[1]SZ[19]
> PB[darkforest]
> PW[KOBAYASHI Koichi]
> DT[2016-03
SGF is here.
(;GM[1]SZ[19]
PB[darkforest]
PW[KOBAYASHI Koichi]
DT[2016-03-23]
RE[W+R]HA[3]KM[0.5]TM[1800]RU[Japanese]
AB[pd][dp][pp]
;W[de];B[dc];W[cc];B[ci];W[db];B[ec];W[cd];B[ic];W[cn];B[cl]
;W[fq];B[dn];W[cq];B[dq];W[cp];B[co];W[bo];B[do];W[bn];B[cm]
;W[dr];B[er];W[cr];B[eq];W[jp];B[lq];W[fo]
12 matches
Mail list logo
