Jump to: navigation, search

Texel's Tuning Method

412 bytes added, 22:29, 27 June 2019
no edit summary
* N is the number of test positions.
* Ri is the result of the game corresponding to position i; 0 for black win, '''0.5''' for draw and '''1''' for white win.
* qi or qScore corresponding to position i, is the white relative [[Score|valuescore]] returned by from the chess engine [[Quiescence Search|quiescencesearch]] function. The algorithm assumes the qScore function is [ deterministic]. If [[Transposition Table|transposition tables]] or the [[History Heuristic|history heuristic]] is used in the qScore function this may not be the case.
* [[FILE:TexelTuneMathSigmoid.jpg|none|middle]] [[FILE:SigmoidTexelTune.gif|right|frameless|link=]]
: <ref>[ Sigmoid function from Wikipedia]</ref> <ref>[ Logistic function from Wikipedia]</ref> <ref>see also winning probability W in [[Pawn Advantage, Win Percentage, and Elo]]</ref> <ref>[ log-linear 1 / (1 + 10^(-s/4)) , s=-10 to 10] plot by [ Wolfram Alpha]</ref>
* [[Eval Tuning in Deep Thought]]
* [[Michael Buro#GLEM|GLEM]] by [[Michael Buro]]
* [[Gosu]]
* [[Point Value by Regression Analysis]]
* [[RuyTune]]
* [ tuning for the uninformed] by [[Folkert van Heusden]], [[CCC]], November 23, 2017
* [ how to create a labeled epd from pgn?] by [[Erin Dame]], [[CCC]], December 02, 2017 » [[Extended Position Description|EPD]], [[Portable Game Notation|PGN]]
* [ texel tuning] by [[Folkert van Heusden]], [[CCC]], June 01, 2018
* [ Texel Tuning] by Tamás Kuzmics, [[CCC]], July 03, 2018
* [ Texel tuning speed] by [[Vivien Clauzon]], [[CCC]], August 29, 2018
* [ Texel tuning for piece values] by [[Vivien Clauzon]], [[CCC]], December 08, 2018
=External Links=

Navigation menu