Bandit Algorithms for Tree Search - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2007

Bandit Algorithms for Tree Search

Pierre-Arnaud Coquelin
  • Function : Author
  • PersonId : 837679
Rémi Munos
  • Function : Author
  • PersonId : 836863


Bandit based methods for tree search have recently gained popularity when applied to huge trees, e.g. in the game of go [Gelly et al., 2006]. Their efficient exploration of the tree enables to return rapidly a good value, and improve precision if more time is provided. The UCT algorithm [Kocsis and Szepesvari, 2006], a tree search method based on Upper Confidence Bounds (UCB) [Auer et al. 2002], is believed to adapt locally to the effective smoothness of the tree. However, we show that UCT is ''over-optimistic'' in some sense, leading to a worst-case regret that may be very poor. We propose alternative bandit algorithms for tree search. First, a modification of UCT using a confidence sequence that scales exponentially in the horizon depth is analyzed. We then consider Flat-UCB performed on the leaves and provide a finite regret bound with high probability. Then, we introduce and analyze a Bandit Algorithm for Smooth Trees (BAST) which takes into account actual smoothness of the rewards for performing efficient ''cuts'' of sub-optimal branches with high confidence. Finally, we present an incremental tree expansion which applies when the full tree is too big (possibly infinite) to be entirely represented and show that with high probability, only the optimal branches are indefinitely developed. We illustrate these methods on a global optimization problem of a continuous function, given noisy values.
Fichier principal
Vignette du fichier
BAST.pdf (230.68 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

inria-00150207 , version 1 (29-05-2007)


  • HAL Id : inria-00150207 , version 1


Pierre-Arnaud Coquelin, Rémi Munos. Bandit Algorithms for Tree Search. Uncertainty in Artificial Intelligence, 2007, Vancouver, Canada. ⟨inria-00150207⟩
475 View
323 Download


Gmail Facebook Twitter LinkedIn More