From 0dbc72d82e7f5f314499b22a04dcef45edcdba9a Mon Sep 17 00:00:00 2001 From: Joost VandeVondele Date: Sun, 14 Jul 2019 14:47:50 +0200 Subject: [PATCH] UCI_Elo implementation (#2225) This exploits the recent fractional Skill Level, and is a result from some discussion in #2221 and the older #758. Basically, if UCI_LimitStrength is set, it will internally convert UCI_Elo to a matching fractional Skill Level. The Elo estimate is based on games at TC 60+0.6, Hash 64Mb, 8moves_v3.pgn, rated with Ordo, anchored to goldfish1.13 (CCRL 40/4 ~2000). Note that this is mostly about internal consistency, the anchoring to CCRL is a bit weak, e.g. within this tournament, goldfish and sungorus only have a 200Elo difference, their rating difference on CCRL is 300Elo. I propose that we continue to expose 'Skill Level' as an UCI option, for backwards compatibility. The result of a tournament under those conditions are given by the following table, where the player name reflects the UCI_Elo. # PLAYER : RATING ERROR POINTS PLAYED (%) CFS(%) 1 Elo2837 : 2792.2 50.8 536.5 711 75 100 2 Elo2745 : 2739.0 49.0 487.5 711 69 100 3 Elo2654 : 2666.4 49.2 418.0 711 59 100 4 Elo2562 : 2604.5 38.5 894.5 1383 65 100 5 Elo2471 : 2515.2 38.1 651.5 924 71 100 6 Elo2380 : 2365.9 35.4 478.5 924 52 100 7 Elo2289 : 2290.0 28.0 864.0 1596 54 100 8 sungorus1.4 : 2204.9 27.8 680.5 1596 43 60 9 Elo2197 : 2201.1 30.1 523.5 924 57 100 10 Elo2106 : 2103.8 24.5 730.5 1428 51 100 11 Elo2014 : 2030.5 30.3 377.5 756 50 98 12 goldfish1.13 : 2000.0 ---- 511.0 1428 36 100 13 Elo1923 : 1928.5 30.9 641.5 1260 51 100 14 Elo1831 : 1829.0 42.1 370.5 756 49 100 15 Elo1740 : 1738.3 42.9 277.5 756 37 100 16 Elo1649 : 1625.0 42.1 525.5 1260 42 100 17 Elo1558 : 1521.5 49.9 298.0 756 39 100 18 Elo1467 : 1471.3 51.3 246.5 756 33 100 19 Elo1375 : 1407.1 51.9 183.0 756 24 --- It can be observed that all set Elos correspond within the error bars with the observed Ordo rating. No functional change --- Readme.md | 11 ++++++++++- src/search.cpp | 13 ++++++++++--- src/ucioption.cpp | 2 ++ 3 files changed, 22 insertions(+), 4 deletions(-) diff --git a/Readme.md b/Readme.md index be324763..10ffdeae 100644 --- a/Readme.md +++ b/Readme.md @@ -55,7 +55,16 @@ Currently, Stockfish has the following UCI options: Leave at 1 for best performance. * #### Skill Level - Lower the Skill Level in order to make Stockfish play weaker. + Lower the Skill Level in order to make Stockfish play weaker (see also UCI_LimitStrength). + Internally, MultiPV is enabled, and with a certain probability depending on the Skill Level a + weaker move will be played. + + * #### UCI_LimitStrength + Enable weaker play aiming for an Elo rating as set by UCI_Elo. This option overrides Skill Level. + + * #### UCI_Elo + If enabled by UCI_LimitStrength, aim for an engine strength of the given Elo. + This Elo rating has been calibrated at a time control of 60s+0.6s and anchored to CCRL 40/4. * #### Move Overhead Assume a time delay of x ms due to network and GUI overheads. This is useful to diff --git a/src/search.cpp b/src/search.cpp index df19108f..2c2321ee 100644 --- a/src/search.cpp +++ b/src/search.cpp @@ -271,7 +271,7 @@ void MainThread::search() { // Check if there are threads with a better score than main thread if ( Options["MultiPV"] == 1 && !Limits.depth - && !Skill(Options["Skill Level"]).enabled() + && !(Skill(Options["Skill Level"]).enabled() || Options["UCI_LimitStrength"]) && rootMoves[0].pv[0] != MOVE_NONE) { std::map votes; @@ -335,11 +335,18 @@ void Thread::search() { beta = VALUE_INFINITE; multiPV = Options["MultiPV"]; + // Pick integer skill levels, but non-deterministically round up or down // such that the average integer skill corresponds to the input floating point one. + // UCI_Elo is converted to a suitable fractional skill level, using anchoring + // to CCRL Elo (goldfish 1.13 = 2000) and a fit through Ordo derived Elo + // for match (TC 60+0.6) results spanning a wide range of k values. PRNG rng(now()); - int intLevel = int(Options["Skill Level"]) + - ((Options["Skill Level"] - int(Options["Skill Level"])) * 1024 > rng.rand() % 1024 ? 1 : 0); + double floatLevel = Options["UCI_LimitStrength"] ? + clamp(std::pow((Options["UCI_Elo"] - 1346.6) / 143.4, 1 / 0.806), 0.0, 20.0) : + double(Options["Skill Level"]); + int intLevel = int(floatLevel) + + ((floatLevel - int(floatLevel)) * 1024 > rng.rand() % 1024 ? 1 : 0); Skill skill(intLevel); // When playing with strength handicap enable MultiPV search that we will diff --git a/src/ucioption.cpp b/src/ucioption.cpp index 813a0890..23c0c480 100644 --- a/src/ucioption.cpp +++ b/src/ucioption.cpp @@ -74,6 +74,8 @@ void init(OptionsMap& o) { o["nodestime"] << Option(0, 0, 10000); o["UCI_Chess960"] << Option(false); o["UCI_AnalyseMode"] << Option(false); + o["UCI_LimitStrength"] << Option(false); + o["UCI_Elo"] << Option(1350, 1350, 2850); o["SyzygyPath"] << Option("", on_tb_path); o["SyzygyProbeDepth"] << Option(1, 1, 100); o["Syzygy50MoveRule"] << Option(true); -- 2.39.2