EUVIMEDEUVIMED entdecken
Crossref

No-Regret Strategy Solving in Imperfect-Information Games via Pre-Trained Embedding

Yanchang Fu, Shengda Liu, Pei Xu, Kaiqi Huang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (20) · 16906-16913

DOI: 10.1609/aaai.v40i20.38736 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yanchang Fu und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High-quality information set abstraction remains a core challenge in solving large-scale imperfect-information extensive-form games (IIEFGs)--such as no-limit Texas Hold’em--where the finite nature of spatial resources hinders solving strategies for the full game. State-of-the-art AI methods rely on pre-trained discrete clustering for abstraction, yet their hard classification irreversibly discards critical information: specifically, the quantifiable subtle differences between information sets--vital for strategy solving--thus compromising the quality of such solving. Inspired by the word embedding paradigm in natural language processing, this paper proposes the Embedding CFR algorithm, a novel approach for solving strategies in IIEFGs within an embedding space. The algorithm pre-trains and embeds the features of individual information sets into an interconnected low-dimensional continuous space, where the resulting vectors more precisely capture both the distinctions and connections between information sets. Embedding CFR introduces a strategy-solving process driven by regret accumulation and strategy updates in this embedding space, with supporting theoretical analysis verifying its ability to reduce cumulative regret. Experiments on poker show that with the same spatial overhead, Embedding CFR achieves significantly faster exploitability convergence compared to cluster-based abstraction algorithms, confirming its effectiveness. Furthermore, to our knowledge, it is the first algorithm in poker AI that pre-trains information set abstractions via low-dimensional embedding for strategy solving.

Zitieren

APA

Fu, Y., Liu, S., Xu, P., & Huang, K. (2026). No-Regret Strategy Solving in Imperfect-Information Games via Pre-Trained Embedding. Proceedings of the AAAI Conference on Artificial Intelligence, 40(20), 16906-16913. https://doi.org/10.1609/aaai.v40i20.38736

Vancouver

Fu Y, Liu S, Xu P, Huang K. No-Regret Strategy Solving in Imperfect-Information Games via Pre-Trained Embedding. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(20):16906-16913. doi:10.1609/aaai.v40i20.38736

BibTeX
@article{Fu2026,
  author = {Fu, Yanchang and Liu, Shengda and Xu, Pei and Huang, Kaiqi},
  title = {No-Regret Strategy Solving in Imperfect-Information Games via Pre-Trained Embedding},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {20},
  pages = {16906--16913},
  doi = {10.1609/aaai.v40i20.38736}
}
Kostenlos starten →