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

--===============5204870962573890373==
Content-Type: multipart/alternative; boundary="000000000000ec168f059d24b675"

--000000000000ec168f059d24b675
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

Building an opening book is a good idea. I do it too.

By the way, if anybody is interested, I have put a small 9x9 opening book
online:
https://www.crazy-sensei.com/book/go_9x9/
Evaluation is +1 for a win, -1 for a loss, for a komi of 7. It may not be
very good, because evaluations was done by my 19x19 network. I have started
to train a specialized 9x9 network last week, and it is already stronger.

R=C3=A9mi

--000000000000ec168f059d24b675
Content-Type: text/html; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

<div dir=3D"ltr"><div>Building an opening book is a good idea. I do it too.=
</div><div><br></div><div>By the way, if anybody is interested, I have put =
a small 9x9 opening book online:</div><div><a href=3D"https://www.crazy-sen=
sei.com/book/go_9x9/">https://www.crazy-sensei.com/book/go_9x9/</a></div><d=
iv></div><div>Evaluation is +1 for a win, -1 for a loss, for a komi of 7. I=
t may not be very good, because evaluations was done by my 19x19 network. I=
 have started to train a specialized 9x9 network last week, and it is alrea=
dy stronger.</div><div><br></div><div>R=C3=A9mi<br></div></div>

--000000000000ec168f059d24b675--

--===============5204870962573890373==
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

--===============5204870962573890373==--