Continuous Upper Confidence Trees - Archive ouverte HAL Access content directly
Conference Papers Year : 2011

Continuous Upper Confidence Trees

Abstract

Upper Confidence Trees are a very efficient tool for solving Markov Decision Processes; originating in difficult games like the game of Go, it is in particular surprisingly efficient in high dimensional problems. It is known that it can be adapted to continuous domains in some cases (in particular continuous action spaces). We here present an extension of Upper Confidence Trees to continuous stochastic problems. We (i) show a deceptive problem on which the classical Upper Confidence Tree approach does not work, even with arbitrarily large computational power and with progressive widening (ii) propose an improvement, termed double-progressive widening, which takes care of the compromise between variance (we want infinitely many simulations for each action/state) and bias (we want sufficiently many nodes to avoid a bias by the first nodes) and which extends the classical progressive widening (iii) discuss its consistency and show experimentally that it performs well on the deceptive problem and on experimental benchmarks. We guess that the double-progressive widening trick can be used for other algorithms as well, as a general tool for ensuring a good bias/variance compromise in search algorithms.
Fichier principal
Vignette du fichier
c0mcts.pdf (315.19 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00542673 , version 1 (03-12-2010)
hal-00542673 , version 2 (24-07-2011)

Identifiers

  • HAL Id : hal-00542673 , version 2

Cite

Adrien Couёtoux, Jean-Baptiste Hoock, Nataliya Sokolovska, Olivier Teytaud, Nicolas Bonnard. Continuous Upper Confidence Trees. LION'11: Proceedings of the 5th International Conference on Learning and Intelligent OptimizatioN, Jan 2011, Italy. pp.TBA. ⟨hal-00542673v2⟩
457 View
4246 Download

Share

Gmail Facebook X LinkedIn More