Timeline for In chess engines (A.I) how are the values for Piece-Square Tables for simplified evlaution function determined?
Current License: CC BY-SA 4.0
4 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Oct 6, 2023 at 12:48 | comment | added | AspectOfTheNoob | @AbsoluteIdiot The 2 modern approaches used are SPSA tuning and a modern variant of texel-tuning. The former is based on playing hundreds of thousands to millions of games to find the optimal values for certain hyperparameters in the search and evaluation of an engine, and the latter uses gradient descent with positions labeled as Win, Draw, or Loss, and applies a logistic regression based on a sigmoid of the evaluation function(You can read more about texel tuning github.com/AndyGrant/Ethereal/tree/master/src here and chessprogramming.org/Texel%27s_Tuning_Method) | |
| Jul 8, 2018 at 12:11 | comment | added | Fred Knight | chessprogramming.wikispaces.com/… explains it better. Larry Kaufman was the one who tweaked these numbers based on statistics from games. The simple tables were just guesses based on chess pattern recognition. | |
| Jul 8, 2018 at 10:57 | comment | added | Absolute Idiot | How are the values determined ? What method or algorithm is used to determine the values for Piece square table ? Is it some numbers based on our assumptions for a particular piece ? | |
| Jul 7, 2018 at 19:27 | history | answered | Fred Knight | CC BY-SA 4.0 |