Monte Carlo *-minimax search

Authors:
Marc Lanctot;Abdallah Saffidine;Joel Veness;Christopher Archibald;Mark H. M. Winands
Affiliations:
Department of Knowledge Engineering, Maastricht University, Netherlands;LAMSADE, Université Paris-Dauphine, France;Department of Computing Science, University of Alberta, Canada;Department of Computing Science, University of Alberta, Canada;Department of Knowledge Engineering, Maastricht University, Netherlands
Venue:
IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence
Year:
2013

Citing 10
Cited 0

Toward an analysis of forward pruning

Toward an analysis of forward pruning
Finite-time Analysis of the Multiarmed Bandit Problem

Machine Learning
An Adaptive Sampling Algorithm for Solving Markov Decision Processes

Operations Research
A sparse sampling algorithm for near-optimal planning in large Markov decision processes

IJCAI'99 Proceedings of the 16th international joint conference on Artificial intelligence - Volume 2
The *-minimax search procedure for trees containing chance nodes

Artificial Intelligence
CHANCEPROBCUT: forward pruning in chance nodes

CIG'09 Proceedings of the 5th international conference on Computational Intelligence and Games
Efficient selectivity and backup operators in Monte-Carlo tree search

CG'06 Proceedings of the 5th international conference on Computers and games
Bandit based monte-carlo planning

ECML'06 Proceedings of the 17th European conference on Machine Learning
Continuous upper confidence trees

LION'05 Proceedings of the 5th international conference on Learning and Intelligent Optimization
Rediscovering *-MINIMAX search

CG'04 Proceedings of the 4th international conference on Computers and Games

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper introduces Monte Carlo *-Minimax Search (MCMS), a Monte Carlo search algorithm for turned-based, stochastic, two-player, zero-sum games of perfect information. The algorithm is designed for the class of densely stochastic games; that is, games where one would rarely expect to sample the same successor state multiple times at any particular chance node. Our approach combines sparse sampling techniques from MDP planning with classic pruning techniques developed for adversarial expectimax planning. We compare and contrast our algorithm to the traditional *-Minimax approaches, as well as MCTS enhanced with the Double Progressive Widening, on four games: Pig, EinStein Würfelt Nicht!, Can't Stop, and Ra. Our results show that MCMS can be competitive with enhanced MCTS variants in some domains, while consistently outperforming the equivalent classic approaches given the same amount of thinking time.