DocumentCode :
3546941
Title :
Online and offline learning in multi-objective Monte Carlo Tree Search
Author :
Perez, Diego ; Samothrakis, Spyridon ; Lucas, Simon
Author_Institution :
Sch. of Comput. Sci. & Electron. Eng., Univ. of Essex, Colchester, UK
fYear :
2013
fDate :
11-13 Aug. 2013
Firstpage :
1
Lastpage :
8
Abstract :
Multi-Objective optimization has traditionally been applied to manufacturing, engineering or finance, with little impact in games research. However, its application to this field of study may provide interesting results, especially for games that are complex or long enough that long-term planning is not trivial and/or a good level of play depends on balancing several strategies within the game. This paper proposes a new Multi-Objective algorithm based on Monte Carlo Tree Search (MCTS). The algorithm is tested in two different scenarios and its learning capabilities are measured in an online and offline fashion. Additionally, it is compared with a state of the art multi-objective evolutionary algorithm (NSGA-II) and with a previously published Multi-Objective MCTS algorithm. The results show that our proposed algorithm provides similar or better results than other techniques.
Keywords :
Monte Carlo methods; computer games; genetic algorithms; learning (artificial intelligence); trees (mathematics); NSGA-II algorithm; game strategy; games research; learning capabilities; multiobjective Monte Carlo tree search; multiobjective evolutionary algorithm; multiobjective optimization algorithm; nondominated sorting genetic algorithm; offline learning; online learning; Frequency modulation; Games; Marine vehicles; Monte Carlo methods; Optimization; Real-time systems; Vectors;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computational Intelligence in Games (CIG), 2013 IEEE Conference on
Conference_Location :
Niagara Falls, ON
ISSN :
2325-4270
Print_ISBN :
978-1-4673-5308-3
Type :
conf
DOI :
10.1109/CIG.2013.6633621
Filename :
6633621
Link To Document :
بازگشت