From Chessprogramming wiki
Revision as of 08:34, 9 September 2021 by Phhnguyen (talk | contribs) (2020 ...)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

Home * Evaluation

Wassily Kandinsky - Schach-Theorie, 1937 [1]

a heuristic function to determine the relative value of a position, i.e. the chances of winning. If we could see to the end of the game in every line, the evaluation would only have values of -1 (loss), 0 (draw), and 1 (win), and the chess engine should search to depth 1 only to get the best move. In practice, however, we do not know the exact value of a position, so we must make an approximation with the main purpose is to compare positions, and the chess engine now must search deeply and find the highest score position within a given period.

Recently, there are two main ways to build an evaluation: traditional hand-crafted evaluation (HCE) and multi-layer neural networks. This page focuses on the traditional way considering explicit features of a chess position.

Beginning chess players learn to do this starting with the value of the pieces themselves. Computer evaluation functions also use the value of the material balance as the most significant aspect and then add other considerations.

Where to Start

The first thing to consider when writing an evaluation function is how to score a move in Minimax or the more common NegaMax framework. While Minimax usually associates the white side with the max-player and black with the min-player and always evaluates from the white point of view, NegaMax requires a symmetric evaluation in relation to the side to move. We can see that one must not score the move per se – but the result of the move (i.e. a positional evaluation of the board as a result of the move). Such a symmetric evaluation function was first formulated by Claude Shannon in 1949 [2] :

f(p) = 200(K-K')
       + 9(Q-Q')
       + 5(R-R')
       + 3(B-B' + N-N')
       + 1(P-P')
       - 0.5(D-D' + S-S' + I-I')
       + 0.1(M-M') + ...

KQRBNP = number of kings, queens, rooks, bishops, knights and pawns
D,S,I = doubled, blocked and isolated pawns
M = Mobility (the number of legal moves)

Here, we can see that the score is returned as a result of subtracting the current side's score from the equivalent evaluation of the opponent's board scores (indicated by the prime letters K' Q' and R'.. ).

Side to move relative

In order for NegaMax to work, it is important to return the score relative to the side being evaluated. For example, consider a simple evaluation, which considers only material and mobility:

materialScore = kingWt  * (wK-bK)
              + queenWt * (wQ-bQ)
              + rookWt  * (wR-bR)
              + knightWt* (wN-bN)
              + bishopWt* (wB-bB)
              + pawnWt  * (wP-bP)

mobilityScore = mobilityWt * (wMobility-bMobility)

return the score relative to the side to move (who2Move = +1 for white, -1 for black):

Eval  = (materialScore + mobilityScore) * who2Move

Linear vs. Nonlinear

Most evaluations terms are a linear combination of independent features and associated weights in the form of


A function f is linear if the function is additive:


and second if the function is homogeneous of degree 1:


It depends on the definition and independence of features and the acceptance of the axiom of choice (Ernst Zermelo 1904), whether additive real number functions are linear or not [3] . Features are either related to single pieces (material), their location (piece-square tables), or more sophisticated, considering interactions of multiple pawns and pieces, based on certain patterns or chunks. Often several phases to first process simple features and after building appropriate data structures, in consecutive phases more complex features based on patterns and chunks are used.

Based on that, to distinguish first-order, second-order, etc. terms, makes more sense than using the arbitrary terms linear vs. nonlinear evaluation [4] . With respect to tuning, one has to take care that features are independent, which is not always that simple. Hidden dependencies may otherwise make the evaluation function hard to maintain with undesirable nonlinear effects.

General Aspects

Basic Evaluation Features

Considering Game Phase



See also

Search versus Evaluation



1950 ...

1960 ...

1970 ...

1980 ...

1990 ...

2000 ...

2010 ...

2015 ...

Blog & Forum Posts

1993 ...

1995 ...

2000 ...

2005 ...

Re: Search or Evaluation? by Mark Uniacke, Hiarcs Forum, October 14, 2007

2010 ...





2015 ...




2020 ...


Re: Idea: use range (evalMin - evalMax) for position evaluation by Álvaro Begué, LCZero Forum, May 28, 2021 [12]
Re: Idea: use range (evalMin - evalMax) for position evaluation by Warren D. Smith, LCZero Forum, May 29, 2021

External Links

Mathematical Foundations

Chess Evaluation


Up one level