Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: An idea to generate a new test suite that is not only tactics

Author: Dann Corbit

Date: 00:31:31 01/16/01

Go up one level in this thread


On January 16, 2001 at 02:33:14, Pete Galati wrote:

>On January 15, 2001 at 13:06:38, Dann Corbit wrote:
>
>>On January 15, 2001 at 13:01:39, Uri Blass wrote:
>>
>>>On January 15, 2001 at 12:56:14, Dann Corbit wrote:
>>>
>>>>On January 15, 2001 at 12:24:10, Uri Blass wrote:
>>>>
>>>>>It is possible to use some games and a lot of computer time to genrate a test
>>>>>suite.
>>>>>
>>>>>The idea is to give some top programs to analyze all the positions in the games
>>>>>and to give them 24 hours per position.
>>>>>
>>>>>The test suite can include all the positions that there was an agreement between
>>>>>all the top programs about the best move after 24 hours of search when part of
>>>>>them needed more than 3 minutes to converge to the best move(otherwise the
>>>>>position is too easy).
>>>>>
>>>>>People can claim that the fact that all of the program converge to the same move
>>>>>is not a proof that it is the best move and I agree but I think that in
>>>>>more than 90% of the cases the solution will be correct.
>>>>
>>>>On the SSDF is a positional test suite similar to the one that you propose.
>>>
>>>I remember that the test suite of the ssdf give some options for every move when
>>>there is not only one move.
>>>
>>>It is impossible to give more than one option in my test.
>>>
>>>I also have doubts about the question if the solutions are correct.
>>>
>>>If I know that all top programs converge after 24 hours to the solution then I
>>>believe more in the test.
>>
>>The reason that I mention that particular test is because it is very thoroughly
>>documented.
>>
>>I refer (of course) to this one:
>>
>>Given this search:
>>http://www.google.com/search?q=berkeley+sis
>>
>>This is the 3rd listing:
>>http://home.interact.se/~w100107/fentest.htm
>
>I converted these from fen to epd, some programs choke when you try to feed them
>fen notation.
>
>1r2r1k1/1pqbbppp/p2p1n2/4p3/P3PP2/2N1BB2/1PP2QPP/R4R1K b - - 0 1
>r1bk1bnr/ppp2ppp/8/4n3/2P5/P3B3/1P3PPP/RN2KBNR w KQ - 0 1
>8/7p/3k2p1/6P1/4KP2/8/7P/8 w - - 0 1
>r1b1r1k1/1p1n1pbp/2p1n1p1/q1P1p3/4P3/1PN1BNPP/2Q2PB1/1R1R2K1 w - - 0 1; id "4";
>1rN1r1k1/1pq2pp1/2p1nn1p/p2p1B2/3P4/4P2P/PPQ1NPP1/2R2RK1 b - - 0 1; id "5";
>3r1rk1/p1q2pbp/1np1p1p1/1p2P3/5P2/2N2Q1P/PPP3P1/3RRBK1 b - - 0 1; id "6";
>r2r2k1/p3ppbp/1p4p1/3p4/3P4/2P1P2P/P3BPP1/2R2RK1 w - - 0 1
>2rq3r/pb1pbkpp/1p2pp2/n1P5/2P5/QP2BNPB/P3PP1P/3R1RK1 w - - 0 1; id "8";
>1r1q1rk1/pp1bbppp/2n1p1n1/4P3/2BpN3/3P1N2/PP2QPPP/R1B1R1K1 b - - 0 1; id "9";
>3r2k1/2p2ppp/1p1br3/pPn5/3PP3/P7/1B1N2PP/R3R1K1 w - - 0 1; id "10";
>r4rk1/p2qn1bp/1pnp2p1/2p2p2/4PP1N/2PPB3/PP2QN1P/R4RK1 b - - 0 1; id "11";
>r3r1k1/1b1n1p2/1q1p1n1p/2p1p2P/p1P3p1/P1QNPPB1/1P2B1P1/2KR3R w - - 0 1; id "12";
>1rb1nrk1/2q1bppp/p1n1p3/2p1P3/2Pp1PP1/3P1NN1/P5BP/R1BQ1RK1 w - - 0 1; id "13";
>r3r1k1/ppqbbpp1/2pp1nnp/3Pp3/2P1P3/5N1P/PPBN1PP1/R1BQR1K1 w - - 0 1; id "14";
>5r1k/1q2rnpp/p4p2/1pp5/6Q1/1P3P2/PBP3PP/3RR1K1 w - - 0 1; id "15";
>2r2k2/5p2/2Bp1b1r/2qPp1pp/PpN1P3/1P2Q3/5PPP/4R1K1 w - - 0 1; id "16";
>
>The ones with more crowded boards, I added an ID # to, the rest I left blank.
>This looks like a good test suite to me actually, but I didn't run any of these
>past any programs yet.

Here's the one I made up from it:

[D]1r2r1k1/1pqbbppp/p2p1n2/4p3/P3PP2/2N1BB2/1PP2QPP/R4R1K b - - bm Rbc8; c0
"positional scores are: Rbc8=10, exf4=9, Bc6=7, Rec8=6, b6=6, b5=5, Be6=4,
h6=3"; id "tony.pos.01";
[D]r1bk1bnr/ppp2ppp/8/4n3/2P5/P3B3/1P3PPP/RN2KBNR w - - bm Nf3; c0 "positional
scores are: Nf3=10, Nd2=9, Nc3=7, Be2=6, Bf4=4, f4=3, h3=3"; id "tony.pos.02";
[D]8/7p/3k2p1/6P1/4KP2/8/7P/8 w - - bm h4; c0 "positional scores are: h4=10,
Kf3=8, Ke3=6, Kd4=6, Kd3=6, h3=5"; id "tony.pos.03";
[D]r1b1r1k1/1p1n1pbp/2p1n1p1/q1P1p3/4P3/1PN1BNPP/2Q2PB1/1R1R2K1 w - - bm Rb2; c0
"positional scores are: Rb2=10, Na4=8, b4=7, Nd2=6, Qb2=5, Bf1=5, Rd2=4, Ne2=3,
Kh2=3, Ra1=1"; id "tony.pos.04";
[D]1rN1r1k1/1pq2pp1/2p1nn1p/p2p1B2/3P4/4P2P/PPQ1NPP1/2R2RK1 b - - bm Rexc8; c0
"positional scores are: Rexc8=10, Rbxc8=7, Qxc8=7"; id "tony.pos.05";
[D]3r1rk1/p1q2pbp/1np1p1p1/1p2P3/5P2/2N2Q1P/PPP3P1/3RRBK1 b - - bm Rxd1; c0
"positional scores are: Rxd1=10, f5=9, Na4=7, Nd5=5, a6=5, f6=4, g5=3"; id
"tony.pos.06";
[D]r2r2k1/p3ppbp/1p4p1/3p4/3P4/2P1P2P/P3BPP1/2R2RK1 w - - bm f4; c0 "positional
scores are: f4=10, Ba6=8, c4=7, a4=5, Rfd1=4"; id "tony.pos.07";
[D]2rq3r/pb1pbkpp/1p2pp2/n1P5/2P5/QP2BNPB/P3PP1P/3R1RK1 w - - bm b4; c0
"positional scores are: b4=10, Nd4=8, Rd2=5, Qc1=5"; id "tony.pos.08";
[D]1r1q1rk1/pp1bbppp/2n1p1n1/4P3/2BpN3/3P1N2/PP2QPPP/R1B1R1K1 b - - bm b5; c0
"positional scores are: b5=10, Ngxe5=9, Ncxe5=9, Qc7=8, Na5=7, a6=6, h6=5,
f6=3"; id "tony.pos.09";
[D]3r2k1/2p2ppp/1p1br3/pPn5/3PP3/P7/1B1N2PP/R3R1K1 w - - bm Re2; c0 "positional
scores are: Re2=10, d5=8, Nc4=7, e5=6, dxc5=5"; id "tony.pos.10";
[D]r4rk1/p2qn1bp/1pnp2p1/2p2p2/4PP1N/2PPB3/PP2QN1P/R4RK1 b - - bm d5; c0
"positional scores are: d5=10, Bh6=8, Rae8=7, fxe4=5"; id "tony.pos.11";
[D]r3r1k1/1b1n1p2/1q1p1n1p/2p1p2P/p1P3p1/P1QNPPB1/1P2B1P1/2KR3R w - - bm e4; c0
"positional scores are: e4=10, Rh4=8, Nf2=7, Qd2=6, Qc2=5, Bh4=4, Kb1=3"; id
"tony.pos.12";
[D]1rb1nrk1/2q1bppp/p1n1p3/2p1P3/2Pp1PP1/3P1NN1/P5BP/R1BQ1RK1 w - - bm Nd2; c0
"positional scores are: Nd2=10, Qe1=9, Qe2=8, Ne4=7, f5=6, Nh5=6, g5=6, h4=5,
Bd2=4, Bh3=3, Re1=1"; id "tony.pos.13";
[D]r3r1k1/ppqbbpp1/2pp1nnp/3Pp3/2P1P3/5N1P/PPBN1PP1/R1BQR1K1 w - - bm Nb1; c0
"positional scores are: Nb1=10, Rb1=9, Nf1=8, dxc6=5, Nb3=5, b3=4, a3=3, b4=2";
id "tony.pos.14";
[D]5r1k/1q2rnpp/p4p2/1pp5/6Q1/1P3P2/PBP3PP/3RR1K1 w - - bm Re6; c0 "positional
scores are: Re6=10, Kf2=9, h4=6, f4=5, Rxe7=4"; id "tony.pos.15";
[D]2r2k2/5p2/2Bp1b1r/2qPp1pp/PpN1P3/1P2Q3/5PPP/4R1K1 w - - bm Rc1; c0
"positional scores are: Rc1=10, Nb6=8, Qxc5=7, a5=6, Qf3=5, h4=4, Nxe5=2"; id
"tony.pos.16";

You can find it here:
ftp://cap.connx.com/pub/EPD/tony-pos.epd



This page took 0 seconds to execute

Last modified: Thu, 15 Apr 21 08:11:13 -0700

Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.