roshi Yamashita
- Original Message -
From: "Aja Huang"
To:
Sent: Saturday, October 10, 2015 3:44 AM
Subject: Re: [Computer-go] Detlef's DCNN data
Hi Hiroshi,
On Fri, Oct 9, 2015 at 2:10 PM, Hiroshi Yamashita wrote:
Mix MM gamma with CNN is clery stronger. But using only
y CNN's p
p : CNN's probability p
p = result_CNN(pos(x,y));
if ( p < 0.0001 ) p = 0.0001;
p *= 50;
MM_gamma *= p
Regards,
Hiroshi Yamashita
- Original Message -
From: "Aja Huang"
To:
Sent: Monday, October 05, 2015 12:32 AM
Subject: Re: [Computer-go] Detlef'
From: "Aja Huang"
To:
Sent: Monday, October 05, 2015 12:32 AM
Subject: Re: [Computer-go] Detlef's DCNN data
Hi Hiroshi,
On Fri, Sep 18, 2015 at 7:08 PM, Hiroshi Yamashita wrote:
DCNN returns each move probabilty. I multiply it by 1000, and multiply
it by each move&#
Hm, AyaMC4 is 4d since last year.
AyaMC4 is 10sec/move on 6 cores, about 200,000 playouts/move.
And time setting is blitz, 1 minutes + 15 sec x10.
AyaMC uses same setting, except time is 10 mimutes + 30sec x5.
Its rank is 3d. Aya never get 4d in normal time setting.
Hiroshi Yamashita
_
Aja Huang:
:
>On Fri, Sep 18, 2015 at 7:08 PM, Hiroshi Yamashita wrote:
>>
>> 1 playout Aya with DCNN vs 1 playout Aya without DCNN.
>> (1 thread, selfplay, Xeon W3680 3.3GHz, GTS 450)
>>
>> winrate wins/games
>> 0.943 83/88r *= 1000
>> 0.897 78/87r *= 500
>> 0.913
Congratulations. Very promising results. I just noticed Aya is now much
Thanks!
AyaMC6 (1 playouts/move + DCNN) got weak 4d after 67 rated games.
Time setting is 10 minutes + 30 sec x5.
Without DCNN, AyaMC2 (1 playouts/move, same time setting)
is 2.7d (from rank graph). So DCNN changes f
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Thanks for the very detailed report! SO good to see, that stronger
programs start using DCNN.
We should ask Nick, if he DCNN gets an exception from the KGS rules.
At the moment I would interpret them as not allowing multiple bots
using the same CNN, b
Hi,
I tried Detlef's DCNN learning data with Aya.
http://computer-go.org/pipermail/computer-go/2015-April/007573.html
I tested 1 playout/move selfplay, and DCNN with Aya got around
90% winrate.
DCNN returns each move probabilty. I multiply it by 1000, and multiply
it by each move's rating.
