Hi Pawel, thanks and glad to see your reply! It reminds me that, it might also be interesting to see the tournament between Rodent-SungEval vs Sungorus, because I feel that, since Rodent is developed based on Sungorus, the sungorus evaluation score would be more compatible to Redoent than Fruit.PK wrote:https://sites.google.com/site/sungorus/
giving it Fruit eval would require rewriting piece/square code - at least this is what I've done in the early version of Rodent. Sungorus uses only one set of piece/square tables, which are vertically symmetrical (!). It updates this score component while making and unmaking moves using one variable (no split for mg/eg and no split for colors). To "frutify" eval it would be needed to split this variable and probably to add incrementally updated game phase variable. At least this is what I've done at the beginning of Rodent
I start to do this from yesterday, by replacing both "ReturnFull" and "ReturnFast" with the sungorus evaluation (not sure whether this make sense, but I just want to keep it simple ), and launched a similar 4000 round tournament. It is not complete yet, around 2600 games have been played, but result is almost clear: Rodent-SungEval won around 80% scores. Here is the BayesElo output:
Code: Select all
Rank Name Elo + - games score oppo. draws
1 rodent_sungeval 107 7 7 2357 79% -107 25%
2 sungorus -107 7 7 2357 21% 107 25%
I will also share my implementation of Rodent-SungEval once the tournament is done. I compile Rodent on RedHat linux, so I made some trivial change on the code. Hope it does not introduce any bugs~