Skip to Main content Skip to Navigation
Theses

Monte Carlo Tree Search for Continuous and Stochastic Sequential Decision Making Problems

Adrien Couetoux 1, 2
2 TAO - Machine Learning and Optimisation
CNRS - Centre National de la Recherche Scientifique : UMR8623, Inria Saclay - Ile de France, UP11 - Université Paris-Sud - Paris 11, LRI - Laboratoire de Recherche en Informatique
Abstract : In this thesis, I studied sequential decision making problems, with a focus on the unit commitment problem. Traditionnaly solved by dynamic programming methods, this problem is still a challenge, due to its high dimension and to the sacrifices made on the accuracy of the model to apply state of the art methods. I investigated on the applicability of Monte Carlo Tree Search methods for this problem, and other problems that are single player, stochastic and continuous sequential decision making problems. In doing so, I obtained a consistent and anytime algorithm, that can easily be combined with existing strong heuristic solvers.
Complete list of metadatas

Cited literature [123 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-00927252
Contributor : Adrien Couetoux <>
Submitted on : Sunday, January 12, 2014 - 11:44:14 AM
Last modification on : Friday, October 23, 2020 - 4:55:06 PM
Long-term archiving on: : Saturday, April 8, 2017 - 2:20:56 PM

Identifiers

  • HAL Id : tel-00927252, version 1

Collections

Citation

Adrien Couetoux. Monte Carlo Tree Search for Continuous and Stochastic Sequential Decision Making Problems. Data Structures and Algorithms [cs.DS]. Université Paris Sud - Paris XI, 2013. English. ⟨tel-00927252⟩

Share

Metrics

Record views

1208

Files downloads

6108