EUVIMEDEUVIMED entdecken
Crossref

Hexaïssa: Standing on Giants’ Shoulders—Routing the Best Chess Engines with Mixture-of-Experts and Latent Reward Learning

Bach Ngo, Nguyen Hoang Khoi Do

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (29) · 24532-24540

DOI: 10.1609/aaai.v40i29.39636 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Bach Ngo und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We present Hexaïssa, a novel framework for adaptive chess engine routing that formulates expert selection as a Mixture-of-Experts (MoE) problem. Hexaïssa learns a gating policy that dynamically selects among heterogeneous state-of-the-art engines—such as Stockfish, LCZero, and Obsidian—based on the tactical and strategic complexity of each board state. This adaptivity enables stronger play and more efficient computation than any fixed engine or static configuration. However, training such a gating policy is fundamentally challenging due to sparse optimization signals and long-horizon credit assignment in chess games. To address these challenges, we introduce a score-based inverse reinforcement learning (IRL) method that models expert engine trajectories as samples from a latent distribution over optimal behaviors. By recovering the Stein score function of this distribution via stochastic differential equations (SDEs), we infer dense, per-move reward signals consistent with potential-based IRL. These latent rewards allow efficient training of the gating network without requiring additional environment interaction or human supervision. Empirical results on standard chess benchmarks demonstrate that Hexaïssa significantly outperforms individual engines, conventional MoE models, and IRL baselines.

Zitieren

APA

Ngo, B., & Do, N. H. K. (2026). Hexaïssa: Standing on Giants’ Shoulders—Routing the Best Chess Engines with Mixture-of-Experts and Latent Reward Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(29), 24532-24540. https://doi.org/10.1609/aaai.v40i29.39636

Vancouver

Ngo B, Do NHK. Hexaïssa: Standing on Giants’ Shoulders—Routing the Best Chess Engines with Mixture-of-Experts and Latent Reward Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(29):24532-24540. doi:10.1609/aaai.v40i29.39636

BibTeX
@article{Ngo2026,
  author = {Ngo, Bach and Do, Nguyen Hoang Khoi},
  title = {Hexaïssa: Standing on Giants’ Shoulders—Routing the Best Chess Engines with Mixture-of-Experts and Latent Reward Learning},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {29},
  pages = {24532--24540},
  doi = {10.1609/aaai.v40i29.39636}
}
Kostenlos starten →