diff options
| author | Scott Gasch <[email protected]> | 2026-09-25 08:44:25 -0700 |
|---|---|---|
| committer | Scott Gasch <[email protected]> | 2026-09-25 08:44:25 -0700 |
| commit | 9b28080f8b3dca4588cb2aaaf748451f45e3c626 (patch) | |
| tree | 54e0aff5d6ee1520c590c7c04a5ae2f8299e7497 /src/eval_tune/test_vs_head.sh | |
| parent | 66740dc89c7351c120c25788d0079055034f4942 (diff) | |
Two ideas:
1. Nullmove R=3 + depth/6 along with some ShouldWeDoNullmoveSearch
tweaking and calibrating.
2. Probe EGTB everywhere in the search as long as the table/position
is resident in memory.
Diffstat (limited to 'src/eval_tune/test_vs_head.sh')
| -rwxr-xr-x | src/eval_tune/test_vs_head.sh | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/src/eval_tune/test_vs_head.sh b/src/eval_tune/test_vs_head.sh index e937389..d6d9fba 100755 --- a/src/eval_tune/test_vs_head.sh +++ b/src/eval_tune/test_vs_head.sh @@ -48,9 +48,9 @@ python3 ./match_play.py \ ${HEAD} \ ${CANDIDATE} \ --pgn ../../pgn/twic_filtered.pgn \ - --games 20000 \ + --games 10000 \ --workers 12 \ - --st 1 \ + --st 4 \ --sprt --elo0 0 --elo1 5 \ --scratch /usr/local/tmp/typhoon_match_${LABEL} \ --log ${LABEL}.log \ |