Monte-Carlo Tree Search by Best Arm Identification - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2017

Monte-Carlo Tree Search by Best Arm Identification


Recent advances in bandit tools and techniques for sequential learning are steadily enabling new applications and are promising the resolution of a range of challenging related problems. We study the game tree search problem, where the goal is to quickly identify the optimal move in a given game tree by sequentially sampling its stochastic payoffs. We develop new algorithms for trees of arbitrary depth, that operate by summarizing all deeper levels of the tree into confidence intervals at depth one, and applying a best arm identification procedure at the root. We prove new sample complexity guarantees with a refined dependence on the problem instance. We show experimentally that our algorithms outperform existing elimination-based algorithms and match previous special-purpose methods for depth-two trees.
Fichier principal
Vignette du fichier
KK17arXiv.pdf (326.61 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-01535907 , version 1 (09-06-2017)
hal-01535907 , version 2 (05-11-2017)



Emilie Kaufmann, Wouter M. Koolen. Monte-Carlo Tree Search by Best Arm Identification. NIPS 2017 - 31st Annual Conference on Neural Information Processing Systems, Dec 2017, Long Beach, United States. pp.1-23. ⟨hal-01535907v2⟩
301 View
478 Download



Gmail Mastodon Facebook X LinkedIn More