Mark H. M. Winands

Mark H. M. Winands

Auto-generated profile, based on publicly available information

Mark H. M. Winands

Maastricht University

Research Focus & Metrics

Academic Career Length

26Years (2001-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2008
Verified
Book Chapter
Closed access
PDF file
GCGuillaume M. J. -B. Chaslot
Guillaume M. J. -B. Chaslot
MWMark H. M. Winands
Mark H. M. Winands
HHH. Jaap van Den Herik
H. Jaap van Den Herik

1 October 2012 in Knowledge-Based Systems
Verified
Journal Article
Closed access
Maarten SchaddMaarten Schadd
Maarten Schadd
MWMark H.M. Winands
Mark H.M. Winands
MTMandy J.W. Tak
Mandy J.W. Tak
JUJos W.H.M. Uiterwijk
Jos W.H.M. Uiterwijk

1 January 2008
Verified
Book Chapter
Closed access
PDF file
Maarten SchaddMaarten Schadd
Maarten Schadd
MWMark H. M. Winands
Mark H. M. Winands
HHH. Jaap van Den Herik
H. Jaap van Den Herik
GCGuillaume M. J. -B. Chaslot
Guillaume M. J. -B. Chaslot
JUJos W. H. M. Uiterwijk
Jos W. H. M. Uiterwijk

26 July 2010 in IEEE Transactions on Computational Intelligence and AI in Games
Verified
Journal Article
Closed access
MWMark H. M. Winands
Mark H. M. Winands
YBYngvi Bjornsson
Yngvi Bjornsson
JSJahn-Takeshi Saito
Jahn-Takeshi Saito
The success of Monte Carlo tree search (MCTS) in many games, where αβ-based search has failed, naturally raises the question whether Monte Carlo simulations will eventually also outperform traditional game-tree search in game domains where αβ -based search is now successful. The forte of αβ-based search are highly tactical deterministic game domains with a small to moderate branching factor, where efficient yet knowledge-rich evaluation functions can be applied effectively. In this paper, we describe an MCTS-based program for playing the game Lines of Action (LOA), which is a highly tactical slow-progression game exhibiting many of the properties difficult for MCTS. The program uses an improved MCTS variant that allows it to both prove the game-theoretical value of nodes in a search tree and to focus its simulations better using domain knowledge. This results in simulations superior in both handling tactics and ensuring game progression. Using the improved MCTS variant, our program is able to outperform even the world's strongest αβ-based LOA program. This is an important milestone for MCTS because the traditional game-tree search approach has been considered to be the better suited for playing LOA.

1 January 2008
Verified
Book Chapter
Closed access
PDF file
MWMark H. M. Winands
Mark H. M. Winands
YBYngvi Björnsson
Yngvi Björnsson
JSJahn-Takeshi Saito
Jahn-Takeshi Saito

4 February 2014 in IEEE Transactions on Computational Intelligence and AI in Games
Verified
Journal Article
Open access
TPTom Pepels
Tom Pepels
MWMark H. M. Winands
Mark H. M. Winands
MLMarc Lanctot
Marc Lanctot
In this paper, Monte Carlo tree search (MCTS) is introduced for controlling the Pac-Man character in the real-time game Ms Pac-Man. MCTS is used to find an optimal path for an agent at each turn, determining the move to make based on the results of numerous randomized simulations. Several enhancements are introduced in order to adapt MCTS to the real-time domain. Ms Pac-Man is an arcade game, in which the protagonist has several goals but no conclusive terminal state. Unlike games such as Chess or Go there is no state in which the player wins the game. Instead, the game has two subgoals, 1) surviving and 2) scoring as many points as possible. Decisions must be made in a strict time constraint of 40 ms. The Pac-Man agent has to compete with a range of different ghost teams, hence limited assumptions can be made about their behavior. In order to expand the capabilities of existing MCTS agents, four enhancements are discussed: 1) a variable-depth tree; 2) simulation strategies for the ghost team and Pac-Man; 3) including long-term goals in scoring; and 4) reusing the search tree for several moves with a decay factor γ. The agent described in this paper was entered in both the 2012 World Congress on Computational Intelligence (WCCI'12, Brisbane, Qld., Australia) and the 2012 IEEE Conference on Computational Intelligence and Games (CIG'12, Granada, Spain) Pac-Man Versus Ghost Team competitions, where it achieved second and first places, respectively. In the experiments, we show that using MCTS is a viable technique for the Pac-Man agent. Moreover, the enhancements improve overall performance against four different ghost teams.