SEP 3, 2026 · PREPRINT
Local Updates, Global Learning (LUGL): Playing Games with non-incremental Learners
arXiv
This is an unrefereed preprint presenting a novel algorithmic framework tested on benchmark games; the work is methodologically sound but lacks peer review, clinical or real-world validation, and independent replication.
Reported
Benchmarks evaluated4 perfect-information games (Tic-tac-toe, C…
ComparatorsDQN, DeepCFR