Current Challenges in Multi-player Game Search

Sturtevant, Nathan R.

doi:10.1007/11674399_20

Cited by 12 publications

(8 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In real games players rarely communicate explicitly before the beginning of a game. This means that they are not guaranteed to be playing the same equilibrium strategy, and, unlike in two-player games, max n does not provide a lower bound on the final payoff in the game when this occurs [8]. In practice it is not always clear which payoffs should be used at leaf nodes.…”

Section: Introductionmentioning

confidence: 99%

An Analysis of Uct in Multi-Player Games

Sturtevant

2008

ICG

Self Cite

View full text Add to dashboard Cite

Abstract. The UCT algorithm has been exceedingly popular for Go, a two-player game, significantly increasing the playing strength of Go programs in a very short time. This paper provides an analysis of the UCT algorithm in multi-player games, showing that UCT, when run in a multi-player game, is computing a mixed-strategy equilibrium, as opposed to max n , which computes a pure-strategy equilibrium. We analyze the performance of UCT in several known domains and show that it performs as well or better than existing algorithms.

show abstract

Section: Introductionmentioning

confidence: 99%

An Analysis of Uct in Multi-Player Games

Sturtevant

2008

ICG

Self Cite

View full text Add to dashboard Cite

show abstract

“…Multiplayer algorithms in imperfect information games have not received much attention. Sturtevant (2004) suggested performing Monte-Carlo sampling and then using the Max n algorithm (Luckhardt & Irani, 1986). We decided not to use this approach because, during the search, the opponent agents act as if they have access to the full information-which results in very unlikely moves.…”

Section: Reasoning In Imperfect Information Gamesmentioning

confidence: 99%

Learning to bid in bridge

Amit

Markovitch

2006

Mach Learn

View full text Add to dashboard Cite

Bridge bidding is considered to be one of the most difficult problems for gameplaying programs. It involves four agents rather than two, including a cooperative agent. In addition, the partial observability of the game makes it impossible to predict the outcome of each action. In this paper we present a new decision-making algorithm that is capable of overcoming these problems. The algorithm allows models to be used for both opponent agents and partners, while utilizing a novel model-based Monte Carlo sampling method to overcome the problem of hidden information. The paper also presents a learning framework that uses the above decision-making algorithm for co-training of partners. The agents refine their selection strategies during training and continuously exchange their refined strategies. The refinement is based on inductive learning applied to examples accumulated for classes of states with conflicting actions. The algorithm was empirically evaluated on a set of bridge deals. The pair of agents that co-trained significantly improved their bidding performance to a level surpassing that of the current state-of-the-art bidding algorithm.

show abstract

“…However, when the branch sizes of the game tree become huge, these approaches can not perform efficiently. Thus, the multiple equilibrium theory and methods are studied recent years as another approach to solve imperfect information games [4]. UCT outperforms alpha-beta search [7] for at least three major advantages.…”

Section: Introductionmentioning

confidence: 99%

A Modified UCT Algorithm Basd on Risk Estimation Methods

Zhang¹,

Wang²

2014

Advanced Science and Technology Letters

View full text Add to dashboard Cite

Abstract. Risk dominance and payoff dominance strategy are two complementary parts of the game theory decision strategy. While payoff dominance is still the basic principle in perfect information, two player games, risk dominance has shown its advantages in imperfect information conditions. In this paper, we first review the related work in the area of estimation methods and the influence of risk factors on computing game equilibrium. Then a new algorithm, UCT-Risk is proposed in this paper, which is a modification of UCT (UCB apply to Trees) algorithm based on risk estimation methods. Finally, we implement the proposed algorithm in SiGuo game, a popular imperfect information game in China. The experimental result of the new algorithm shows it correctness and effectiveness.

show abstract

Current Challenges in Multi-player Game Search

Cited by 12 publications

References 14 publications

An Analysis of Uct in Multi-Player Games

An Analysis of Uct in Multi-Player Games

Learning to bid in bridge

A Modified UCT Algorithm Basd on Risk Estimation Methods

Contact Info

Product

Resources

About