Re: Training an AlphaGo Zero-like algorithm with limited hardware on 7x7 boards

--===============3551485447043871586==
Content-Type: multipart/alternative; boundary="0000000000002dac01059cfeb24f"

--0000000000002dac01059cfeb24f
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

Hi,

Thanks for sharing your experiments.

Your match results are strange. Did you use a komi? You should use a komi
of 9:
https://senseis.xmp.net/?7x7

The final strength of your network looks surprisingly weak. When I started
to develop the Zero version of Crazy Stone, I spend a lot of time
optimizing my method on a single (V100) GPU. I could train a strong network
from scratch in a single day. Using a wrong komi might have hurt you. Also,
on such a small board, it is not so easy to make sure that the self-play
games have enough variety. You'd have to find many balanced random initial
positions in order to avoid replicating the same game again and again.

R=C3=A9mi

--0000000000002dac01059cfeb24f
Content-Type: text/html; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

<div dir=3D"ltr"><div>Hi,</div><div><br></div><div>Thanks for sharing your =
experiments.</div><div><br></div><div>Your match results are strange. Did y=
ou use a komi? You should use a komi of 9:</div><div><a href=3D"https://sen=
seis.xmp.net/?7x7">https://senseis.xmp.net/?7x7</a></div><div><br></div><di=
v>The final strength of your network looks surprisingly weak. When I starte=
d to develop the Zero version of Crazy Stone, I spend a lot of time optimiz=
ing my method on a single (V100) GPU. I could train a strong network from s=
cratch in a single day. Using a wrong komi might have hurt you. Also, on su=
ch a small board, it is not so easy to make sure that the self-play games h=
ave enough variety. You&#39;d have to find many balanced random initial pos=
itions in order to avoid replicating the same game again and again.<br></di=
v><div><br></div><div>R=C3=A9mi<br></div></div>

--0000000000002dac01059cfeb24f--

--===============3551485447043871586==
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

_______________________________________________
Computer-go mailing list
[email protected]
http://computer-go.org/mailman/listinfo/computer-go

--===============3551485447043871586==--