Monte Carlo tree search

In computer science, Monte Carlo tree search (MCTS) is a heuristic search algorithm for some kinds of decision processes, most notably those employed in software that plays board games. In that context MCTS is used to solve the game tree. MCTS was combined with neural networks in 2016 and has been used in multiple board games like Chess, Shogi, Checkers, Backgammon, Contract Bridge, Go, Scrabble, and Clobber as well as in turn-based-strategy video games (such as Total War: Rome II's implementation in the high level campaign AI). History Monte Carlo method The Monte Carlo method, which uses random sampling for deterministic problems which are difficult or impossible to solve using other approaches, dates back to the 1940s. In his 1987 PhD thesis, Bruce Abramson combined minimax search with an expected-outcome model based on random game playouts to the end, instead of the usual static evaluation function. Abramson said the expected-outcome model "is shown to be

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related publications (4)

Related publications

Related people

Related units

Related concepts (11)

Related concepts

Related courses (5)

Related courses

Related lectures (11)

Related lectures

Network of Shortcuts: An Adaptive Data Structure for Tree-Based Search Methods

Andrea Bergamini

In this work we present a novel concept of augmenting a search tree in a packet-processing system with an dditional data structure, a Network of Shortcuts, in order to adapt the search to current input traffic patterns and significantly speed-up the frequently traversed search-tree paths. The method utilizes node statistics gathered from the tree and periodically adjusts the shortcut positions. After an overview of tree-search methods used in networking tasks such as lookup or classification, and a discussion of the impact of typical traffic characteristics, we argue that adding a small number of direct links, or shortcuts, to the few frequently traversed paths can significantly improve performance, at a very low cost. We present a shortcut-placement heuristic, compare our method to a standard caching mechanism and show how the use of different levels of aggregation in a search tree enables to achieve similar results with much fewer entries.

2005

Importance Sampling Tree for Large-scale Empirical Expectation

Olivier Canévet, François Fleuret, Cijo Jose

We propose a tree-based procedure inspired by the Monte-Carlo Tree Search that dynamically modulates an importance-based sampling to prioritize computation, while getting unbiased estimates of weighted sums. We apply this generic method to learning on very large training sets, and to the evaluation of large-scale SVMs. The core idea is to reformulate the estimation of a score - whether a loss or a prediction estimate - as an empirical expectation, and to use such a tree whose leaves carry the samples to focus efforts over the problematic "heavy weight" ones. We illustrate the potential of this approach on three problems: to improve Adaboost and a multi-layer perceptron on 2D synthetic tasks with several million points, to train a large-scale convolution network on several millions deformations of the CIFAR data-set, and to compute the response of a SVM with several hundreds of thousands of support vectors. In each case, we show how it either cuts down computation by more than one order of magnitude and/or allows to get better loss estimates.

2016

Geometric Graph Matching Using Monte Carlo Tree Search

Miguel Amável Dos Santos Pinheiro, Pascal Fua, Jan Kybic

We present an efficient matching method for generalized geometric graphs. Such graphs consist of vertices in space connected by curves and can represent many real world structures such as road networks in remote sensing, or vessel networks in medical imaging. Graph matching can be used for very fast and possibly multimodal registration of images of these structures. We formulate the matching problem as a single player game solved using Monte Carlo Tree Search, which automatically balances exploring new possible matches and extending existing matches. Our method can handle partial matches, topological differences, geometrical distortion, does not use appearance information and does not require an initial alignment. Moreover, our method is very efficient-it can match graphs with thousands of nodes, which is an order of magnitude better than the best competing method, and the matching only takes a few seconds.

Ieee Computer Soc2017

FIN-472: Computational finance

Participants of this course will master computational techniques frequently used in mathematical finance applications. Emphasis will be put on the implementation and practical aspects.

CS-430: Intelligent agents

Software agents are widely used to control physical, economic and financial processes. The course presents practical methods for implementing software agents and multi-agent systems, supported by programming exercises, and the theoretical underpinnings including computational game theory.

CH-351: Molecular dynamics and Monte-Carlo simulations

Introduction to molecular dynamics and Monte-Carlo simulation methods.

Google DeepMind

DeepMind Technologies Limited, doing business as Google DeepMind, is a British-American artificial intelligence research laboratory which serves as a subsidiary of Google. Founded in the UK in 2010, i

AlphaZero

AlphaZero is a computer program developed by artificial intelligence research company DeepMind to master the games of chess, shogi and go. This algorithm uses an approach similar to AlphaGo Zero. O

Computer chess

Computer chess includes both hardware (dedicated computers) and software capable of playing chess. Computer chess provides opportunities for players to practice even in the absence of human opponent