Author

Amine M. Boumaza

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

The Surprising Effectiveness of Approximate Value Iteration in Self-Play

The results demonstrate the surprising effectiveness of AVI: it learns more accurate value functions than those learned by AlphaZero, while its one-step-lookahead greedy policies remain competitive with MCTS-based policies at substantially lower training and inference costs.

Raphaël Boige, Amine M. Boumaza, Bruno Scherrer · 0 citations