Wisdom is knowing how

   little we know -- Socrates

About Company

Other Information

Experiments in computer chess

The value of an evaluation function

What's the value of an evaluation function (EVAL) in a chess program? What's the value of each EVAL component and how much elo do they represent? This page might give some insight.

For this purpose we took ProDeo 1.74 and added a new parameter.

[EVAL = MATERIAL ONLY]

EVAL returns only the material value following the 1|3|3|5|9 rule

Then we run engine-engine matches of 2000 - 4000 fast games, if needed more if the histogram requires so.

Part I - Starting with no evaluation at all, just counting material.

Match	Base Engine	Setting	Win	Draw	Loss	Perc	Remarks
2.1	ProDeo 1.74	minus Piece Square	888	641	488	40.1%	Apparently PST's are worth a lot.  2000 games. Histogram.
2.2	ProDeo 1.74	minus King Safety	1053	665	737	43.5%	After 2400 games a score drop  of 6.5%  Histogram.
2.3	ProDeo 1.74	minus Mobility	1103	536	427	33.6%	After 2000 games an incredible  score drop of 16.4%. Apparently   Mobility is a very dominant EVAL  ingredient. Histogram.
2.4	ProDeo 1.74	minus Pawn Eval	745	597	666	48.0%	After 2400 games only a score  drop of 2%. Histogram.
2.5	ProDeo 1.74	minus Passed Pawns	1099	353	553	36.4%	After 2000 games an incredible  score drop of 13.6%.  Apparently Passed Pawns is  a  very dominant EVAL ingredient.   Histogram.
2.6	ProDeo 1.74	Minus Moderate stuff  - Bishop Pair  - Knight Outposts  - Center Control  - Double attack eval	762	672	569	45.2%	After 2000 games still a score  drop of 4.8% for the somewhat  less dominant EVAL components.  Histogram.

Part III - Stripping the evaluation step by step from its major components until only some minor stuff

               is left.

List of the minor stuff that has remained in EVAL and is responsible for the 9.8%

1. Tuned pieces values for the middle game and end game.
2. Pin evaluation.
3. Subtraction threats evaluation.
4. Xray evaluation.
5. Blocking a weak pawn with a knight.
6. Rook on 7th rank evaluation.
7. Trapped Bishop on a7|h7 and a6|h6
8. Trapped Rook in case of lost castling rights.
9. Quadrant rule in pawn endings.
10. Unequal Bishop ending evaluation.
11. All kind of standard draw evaluation (such KRPKR)
12. Bad Bishop evaluation (bishop caught in its own pawns)
13. Connecting rooks evaluation.
14. Doubled rooks on (semi) open file evaluation.
15. Queen mobility. Her majesty has a separate (very minor) mobility evaluation.
16. Material Imbalance - encourage (avoid) piece exchange when ahead (down) in material.
17. Pawn ending - when 1 pawn up usually wins by 90% evaluation.
18. KPK win or draw evaluation.
19. Avoid early queen development.
20. Castling evaluation.

All these minor evaluations go into one variable and it would require 20 new and separate variable names to meassure their impact on EVAL slowing down the evalauation function which falls outside the scope of this experiment. The 20 points list is convincing enough to explain the remaining 9.8%.