Fewer rows might not give interpretable/​rules-based solutions an advantage. I tried training on only the first 100 or 20 rows, and I got CDEFMW (15.66) and EMOPSV (15.34) as the predicted best meals. Admittedly CDEFMW shows up in the first 100 rows scoring 18 points, but not EMOPSV. Maybe a human with 20 rows could do better by coming up with a lot of hypothetical rules, but it seems tough to beat the black box.
Fewer rows might not give interpretable/​rules-based solutions an advantage. I tried training on only the first 100 or 20 rows, and I got
CDEFMW (15.66)andEMOPSV (15.34)as the predicted best meals. AdmittedlyCDEFMWshows up in the first 100 rows scoring 18 points, but notEMOPSV. Maybe a human with 20 rows could do better by coming up with a lot of hypothetical rules, but it seems tough to beat the black box.