Knowledge-based fast evolutionary MCTS for general video game playing

Pérez, Diego; Samothrakis, Spyridon; Lucas, Simon M.

doi:10.1109/cig.2014.6932868

Cited by 63 publications

(47 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, evolution was used during the simulation phase in a Monte Carlo Tree Search algorithm by Perez et al [19], or, for a different effect, the MCTS parameters were adjusted with evolutionary methods [14]. There has been recent work that has attempted to give more focus to the evolutionary process and instead integrates tree structures into EAs, or uses N-armed bandit techniques and Upper Confidence Bounds (UCB) for informing and guiding the evolution process [13].…”

Section: Relevant Researchmentioning

confidence: 99%

Analysis of Vanilla Rolling Horizon Evolution Parameters in General Video Game Playing

Gaina

Liu

Lucas

et al. 2017

Applications of Evolutionary Computation

View full text Add to dashboard Cite

Abstract. Monte Carlo Tree Search techniques have generally dominated General Video Game Playing, but recent research has started looking at Evolutionary Algorithms and their potential at matching Tree Search level of play or even outperforming these methods. Online or Rolling Horizon Evolution is one of the options available to evolve sequences of actions for planning in General Video Game Playing, but no research has been done up to date that explores the capabilities of the vanilla version of this algorithm in multiple games. This study aims to critically analyse the different configurations regarding population size and individual length in a set of 20 games from the General Video Game AI corpus. Distinctions are made between deterministic and stochastic games, and the implications of using superior time budgets are studied. Results show that there is scope for the use of these techniques, which in some configurations outperform Monte Carlo Tree Search, and also suggest that further research in these methods could boost their performance.

show abstract

Section: Relevant Researchmentioning

confidence: 99%

Analysis of Vanilla Rolling Horizon Evolution Parameters in General Video Game Playing

Gaina

Liu

Lucas

et al. 2017

Applications of Evolutionary Computation

View full text Add to dashboard Cite

show abstract

“…Specifically, combinations of MCTS and EA in GVGAI have been tried in previous works. For instance, Perez et al [11] combined Fast Evolution with MCTS for General Video Game Playing. The objective was to evolve a set of weights W = {w 0 , w 1 , .…”

Section: Hybrids and Hyper-heuristicsmentioning

confidence: 99%

MCTS/EA hybrid GVGAI players and game difficulty estimation

Horn

Volz

Peŕez-Liebana

et al. 2016

2016 IEEE Conference on Computational Intelligence and Games (CIG)

View full text Add to dashboard Cite

Abstract-In the General Video Game Playing competitions of the last years, Monte-Carlo tree search as well as Evolutionary Algorithm based controllers have been successful. However, both approaches have certain weaknesses, suggesting that certain hybrids could outperform both. We envision and experimentally compare several types of hybrids of two basic approaches, as well as some possible extensions. In order to achieve a better understanding of the games in the competition and the strength and weaknesses of different controllers, we also propose and apply a novel game difficulty estimation scheme based on several observable game characteristics.

show abstract

“…Since 2006, the algorithm has been extended with many variations. It is still being used for other computer games [4], including the GVGAI competition [5]. In this paper, we use MCTS as the basis for the new algorithms.…”

Section: B Monte Carlo Tree Searchmentioning

confidence: 99%

Monte Carlo Tree Search with options for general video game playing

Waard

Roijers

Bakkes

2016

2016 IEEE Conference on Computational Intelligence and Games (CIG)

View full text Add to dashboard Cite

Abstract-General video game playing is a challenging research area in which the goal is to find one algorithm that can play many games successfully. "Monte Carlo Tree Search" (MCTS) is a popular algorithm that has often been used for this purpose. It incrementally builds a search tree based on observed states after applying actions. However, the MCTS algorithm always plans over actions and does not incorporate any higher level planning, as one would expect from a human player. Furthermore, although many games have similar game dynamics, often no prior knowledge is available to general video game playing algorithms. In this paper, we introduce a new algorithm called "Option Monte Carlo Tree Search" (O-MCTS). It offers general video game knowledge and high level planning in the form of "options", which are action sequences aimed at achieving a specific subgoal. Additionally, we introduce "Option Learning MCTS" (OL-MCTS), which applies a progressive widening technique to the expected returns of options in order to focus exploration on fruitful parts of the search tree. Our new algorithms are compared to MCTS on a diverse set of twentyeight games from the general video game AI competition. Our results indicate that by using MCTS's efficient tree searching technique on options, O-MCTS outperforms MCTS on most of the games, especially those in which a certain subgoal has to be reached before the game can be won. Lastly, we show that OL-MCTS improves its performance on specific games by learning expected values for options and moving a bias to higher valued options.

show abstract

Knowledge-based fast evolutionary MCTS for general video game playing

Cited by 63 publications

References 10 publications

Analysis of Vanilla Rolling Horizon Evolution Parameters in General Video Game Playing

Analysis of Vanilla Rolling Horizon Evolution Parameters in General Video Game Playing

MCTS/EA hybrid GVGAI players and game difficulty estimation

Monte Carlo Tree Search with options for general video game playing

Contact Info

Product

Resources

About