<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:x="urn:schemas-microsoft-com:office:excel" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40"><head><meta http-equiv=Content-Type content="text/html; charset=utf-8"><meta name=Generator content="Microsoft Word 15 (filtered medium)"><style><!--
/* Font Definitions */
@font-face
        {font-family:"Cambria Math";
        panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
        {font-family:Calibri;
        panose-1:2 15 5 2 2 2 4 3 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
        {margin:0in;
        margin-bottom:.0001pt;
        font-size:12.0pt;
        font-family:"Times New Roman",serif;
        color:black;}
a:link, span.MsoHyperlink
        {mso-style-priority:99;
        color:blue;
        text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
        {mso-style-priority:99;
        color:purple;
        text-decoration:underline;}
span.EmailStyle17
        {mso-style-type:personal-reply;
        font-family:"Calibri",sans-serif;
        color:#1F497D;}
.MsoChpDefault
        {mso-style-type:export-only;
        font-size:10.0pt;}
@page WordSection1
        {size:8.5in 11.0in;
        margin:1.0in 1.0in 1.0in 1.0in;}
div.WordSection1
        {page:WordSection1;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]--></head><body bgcolor=white lang=EN-US link=blue vlink=purple><div class=WordSection1><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D'>The chess result is 64-36: a 100 rating point edge! I think the Stockfish open source project improved Stockfish by ~20 rating points in the last year. Given the number of people/computers involved, Stockfish’s annual effort level seems comparable to the AZ effort.<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D'><o:p> </o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D'>Stockfish is really, really tweaked out to do exactly what it does. It is very hard to improve anything about Stockfish. To be clear: I am not disparaging the code or people or project in any way. The code is great, people are great, project is great. It is really easy to work on Stockfish, but very hard to make progress given the extraordinarily fine balance of resources that already exists.  I tried hard for about 6 months last year without any successes. I tried dozens (maybe 100?) experiments, including several that were motivated by automated tuning or automated searching for opportunities. No luck.<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D'><o:p> </o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D'>AZ would dominate the current TCEC. Stockfish didn’t lose a game in the semi-final, failing to make the final because of too many draws against the weaker players.<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D'><o:p> </o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D'>The Stockfish team will have some self-examination going forward for sure. I wonder what they will decide to do.<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D'><o:p> </o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D'>I hope this isn’t the last we see of these DeepMind programs.<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D'><o:p> </o:p></span></p><div><div style='border:none;border-top:solid #E1E1E1 1.0pt;padding:3.0pt 0in 0in 0in'><p class=MsoNormal><b><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:windowtext'>From:</span></b><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:windowtext'> Computer-go [mailto:computer-go-bounces@computer-go.org] <b>On Behalf Of </b>Richard Lorentz<br><b>Sent:</b> Wednesday, December 6, 2017 12:50 PM<br><b>To:</b> computer-go@computer-go.org<br><b>Subject:</b> Re: [Computer-go] Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm<o:p></o:p></span></p></div></div><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal style='margin-bottom:12.0pt'>One chess result stood out for me, namely, just how much easier it was for AlphaZero to win with white (25 wins, 25 draws, 0 losses) rather than with black (3 wins, 47 draws, 0 losses).<br><br>Maybe we should not give up on the idea of White to play and win in chess!<o:p></o:p></p><div><p class=MsoNormal>On 12/06/2017 01:24 AM, Hiroshi Yamashita wrote:<o:p></o:p></p></div><blockquote style='margin-top:5.0pt;margin-bottom:5.0pt'><p class=MsoNormal><span style='font-size:13.5pt'>Hi, <br><br>DeepMind makes strongest Chess and Shogi programs with AlphaGo Zero method. <br><br>Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm <br><a href="https://urldefense.proofpoint.com/v2/url?u=https-3A__arxiv.org_pdf_1712.01815.pdf&d=DwIGaQ&c=Oo8bPJf7k7r_cPTz1JF7vEiFxvFRfQtp-j14fFwh71U&r=i0hg-cKH69CA5MsdosvezQ&m=w0qxE9GOfBVzqPOT0NBm1nsdQqJMlNu40BOCWfsO-gQ&s=dsola-9J77ArHVeuVc0ZCZKn2nJOsjfsnJzPc_MdPDo&e=">https://urldefense.proofpoint.com/v2/url?u=https-3A__arxiv.org_pdf_1712.01815.pdf&d=DwIGaQ&c=Oo8bPJf7k7r_cPTz1JF7vEiFxvFRfQtp-j14fFwh71U&r=i0hg-cKH69CA5MsdosvezQ&m=w0qxE9GOfBVzqPOT0NBm1nsdQqJMlNu40BOCWfsO-gQ&s=dsola-9J77ArHVeuVc0ZCZKn2nJOsjfsnJzPc_MdPDo&e=</a> <br><br>AlphaZero(Chess) outperformed Stockfish after 4 hours, <br>AlphaZero(Shogi) outperformed elmo after 2 hours. <br><br>Search is MCTS. <br>AlphaZero(Chess) searches     80,000 positions/sec. <br>Stockfish        searches 70,000,000 positions/sec. <br>AlphaZero(Shogi) searches     40,000 positions/sec. <br>elmo             searches 35,000,000 positions/sec. <br><br>Thanks, <br>Hiroshi Yamashita <br><br>_______________________________________________ <br>Computer-go mailing list <br><a href="mailto:Computer-go@computer-go.org">Computer-go@computer-go.org</a> <br><a href="https://urldefense.proofpoint.com/v2/url?u=http-3A__computer-2Dgo.org_mailman_listinfo_computer-2Dgo&d=DwIGaQ&c=Oo8bPJf7k7r_cPTz1JF7vEiFxvFRfQtp-j14fFwh71U&r=i0hg-cKH69CA5MsdosvezQ&m=w0qxE9GOfBVzqPOT0NBm1nsdQqJMlNu40BOCWfsO-gQ&s=Dflm7ezefzMJ9xLNmNYrSQKWa7qvG9FkzlCHngo_NcY&e=">https://urldefense.proofpoint.com/v2/url?u=http-3A__computer-2Dgo.org_mailman_listinfo_computer-2Dgo&d=DwIGaQ&c=Oo8bPJf7k7r_cPTz1JF7vEiFxvFRfQtp-j14fFwh71U&r=i0hg-cKH69CA5MsdosvezQ&m=w0qxE9GOfBVzqPOT0NBm1nsdQqJMlNu40BOCWfsO-gQ&s=Dflm7ezefzMJ9xLNmNYrSQKWa7qvG9FkzlCHngo_NcY&e=</a><o:p></o:p></span></p></blockquote><p class=MsoNormal><o:p> </o:p></p></div></body></html>