oakfoam value network does exactly this, we have 6 komi layers -7.5 -5.5
-0.5 0.5 5.5 7.5 (+ and - due to color played) and trained from 4d+ kgs
games with this:
if (c_played==1):
if ("0.5" in komi):
komiplane=1;
if ("6.5" in komi or "2.75" in komi or "5.5" in komi):
#komi 6.5 and 5.5 not very different in chinese scoring
komiplane=2;
if ("7.5" in komi or "3.75" in komi):
komiplane=3;
if (c_played==2):
if ("0.5" in komi):
komiplane=4;
if ("6.5" in komi or "2.75" in komi or "5.5" in komi):
#komi 6.5 and 5.5 not very different in chinese scoring
komiplane=5;
if ("7.5" in komi or "3.75" in komi):
komiplane=6;
But I was unable to get a sgf file from the japanese language site :)
I did not really test if this layers help, but they are there and
trained and you might check yourself :)
Detlef
Am 21.03.2017 um 21:08 schrieb David Ongaro:
> On Mar 21, 2017, at 7:00 AM, Paweł Morawiecki <pawel.morawie...@gmail.com>
> wrote:
>>
>> Hideki,
>>
>> Using this for Japanese and 6.5, there will be some
>> error in close games. We knew this issue and thought such
>> chances would be so small that postponed correcting (not so
>> easy).
>>
>> But how would you fix it? Isn't that you'd need to retrain your value
>> network from the scratch?
>
> I would think so as well. But I some months ago I already made a proposal in
> this list to mitigate that problem: instead of training a different value
> network for each Komi, add a “Komi adjustment” value as input during the
> training phase. That should be much more effective, since the “win/lost”
> evaluation shouldn’t change for many (most?) positions for small adjustments
> but the resulting value network (when trained for different Komi adjustments)
> has a much greater range of applicability.
>
> Regards
>
> David O.
>
>
>>
>> Oh, so that's why! Good luck with Zen's next two games.
>>
>> Aja
>>
>> Best,
>> Hideki
>>
>> Pawe Morawiecki:
>> <caksbshpvd34hvjt-b+x73rdpg5-4wsxoezykbheslprewci...@mail.gmail.com
>> <mailto:caksbshpvd34hvjt-b%2bx73rdpg5-4wsxoezykbheslprewci...@mail.gmail.com>>:
>>> Hi,
>>>
>>> After an interesting game DeepZen lost to Mi Yu Ting.
>>> Here you can replay the complete game:
>>> http://duiyi.sina.com.cn/gibo_new/live/viewer.asp?sno=13
>>> <http://duiyi.sina.com.cn/gibo_new/live/viewer.asp?sno=13>
>>>
>>> According to pro experts, Zen fought really well, but it seems there is
>>> still some issue how Zen (mis)evaluates its chances. At one point it showed
>>> 84% chance of winning (in the endgame), whereas it was already quite clear
>>> Zen is little behind (2-3 points).
>>>
>>> Regards,
>>> Pawel
>>> ---- inline file
>>> _______________________________________________
>>> Computer-go mailing list
>>> Computer-go@computer-go.org <mailto:Computer-go@computer-go.org>
>>> http://computer-go.org/mailman/listinfo/computer-go
>>> <http://computer-go.org/mailman/listinfo/computer-go>
>> --
>> Hideki Kato <mailto:hideki_ka...@ybb.ne.jp <mailto:hideki_ka...@ybb.ne.jp>>
>> _______________________________________________
>> Computer-go mailing list
>> Computer-go@computer-go.org <mailto:Computer-go@computer-go.org>
>> http://computer-go.org/mailman/listinfo/computer-go
>> <http://computer-go.org/mailman/listinfo/computer-go>
>>
>> _______________________________________________
>> Computer-go mailing list
>> Computer-go@computer-go.org <mailto:Computer-go@computer-go.org>
>> http://computer-go.org/mailman/listinfo/computer-go
>> <http://computer-go.org/mailman/listinfo/computer-go>
>>
>> _______________________________________________
>> Computer-go mailing list
>> Computer-go@computer-go.org <mailto:Computer-go@computer-go.org>
>> http://computer-go.org/mailman/listinfo/computer-go
>> <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
>
_______________________________________________
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
