Beyond Search-Imitation: Prior-Directed Exploration for Searchless Chess
Measuring tactical accuracy and playing strength together across a matched-compute sweep, the two dissociate and a control fine-tuned on puzzles alone posts the study's largest tactical gains while shedding roughly 260 Elo; a better puzzle-solver is not thereby a stronger player.
Szymon Milosz, Piotr Duch, Szymon Grabowski
· 0 citations