DocumentCode
2446821
Title
A UCT agent for Tron: Initial investigations
Author
Samothrakis, Spyridon ; Robles, David ; Lucas, Simon M.
Author_Institution
Sch. of Comput. Sci. & Electron. Eng., Univ. of Essex, Colchester, UK
fYear
2010
fDate
18-21 Aug. 2010
Firstpage
365
Lastpage
371
Abstract
Monte Carlo Tree Search(MCTS) has generated a great deal of excitement in the A.I. community, mainly due to its success in Go. In this paper we test this approach in Tron, a simultaneous move two-agent game. Although the agents created are able to play to a good standard, there is a degree of randomness in their decisions in identical scenarios. This suggests that the success of MCTS is heavily dependent on the suitability of each individual game for Monte-Carlo Simulations.
Keywords
Monte Carlo methods; computer games; multi-agent systems; tree searching; A.I.community; Monte Carlo tree search; Tron; UCT agent; two-agent game; Artificial intelligence; Computer crashes; Conferences; Equations; Games; Humans; Monte Carlo methods;
fLanguage
English
Publisher
ieee
Conference_Titel
Computational Intelligence and Games (CIG), 2010 IEEE Symposium on
Conference_Location
Dublin
Print_ISBN
978-1-4244-6295-7
Electronic_ISBN
978-1-4244-6296-4
Type
conf
DOI
10.1109/ITW.2010.5593331
Filename
5593331
Link To Document