EUVIMEDEUVIMED entdecken
Crossref

Generation and Evaluation of Exploration Terms for Monte Carlo Tree Search

Tristan Cazenave

ICGA Journal: The Journal of the Computer Games Community · 2026-05 · 48 (2) · 62-76

DOI: 10.1177/13896911261463788 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ICGA Journal: The Journal of the Computer Games Community, online erschienen am 09.07.2026. Verfasst von Tristan Cazenave. Die Arbeit nennt 46 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Monte Carlo Tree Search (MCTS) has shown good results for many difficult problems. We propose to automatically generate mathematical expressions that are used as exploration terms for MCTS algorithms, and we evaluate the resulting expressions in the game of Go. We use a systematic generation of small exploration terms. This is in contrast to our initial conference paper, which used Monte Carlo Search to generate exploration terms for Sequential Halving Using Scores (SHUSS). In this journal paper, we extend the work to automatically design three exploration terms: the exploration term near the leaves of Prior Upper Confidence for Trees (PUCT), the exploration term at the root of PUCT and the SHUSS exploration term. All three resulting exploration terms improve upon standard PUCT in the game of Go.

Zitieren

APA

Cazenave, T. (2026). Generation and Evaluation of Exploration Terms for Monte Carlo Tree Search. ICGA Journal: The Journal of the Computer Games Community, 48(2), 62-76. https://doi.org/10.1177/13896911261463788

Vancouver

Cazenave T. Generation and Evaluation of Exploration Terms for Monte Carlo Tree Search. ICGA Journal: The Journal of the Computer Games Community. 2026;48(2):62-76. doi:10.1177/13896911261463788

BibTeX
@article{Cazenave2026,
  author = {Cazenave, Tristan},
  title = {Generation and Evaluation of Exploration Terms for Monte Carlo Tree Search},
  journal = {ICGA Journal: The Journal of the Computer Games Community},
  year = {2026},
  volume = {48},
  number = {2},
  pages = {62--76},
  doi = {10.1177/13896911261463788}
}
Kostenlos starten →