원문정보
초록
영어
As a carrier of artificial intelligence research, computer game can establish a sound theoretical foundation for the research of non-zero-sum card games with imperfect information. In this paper, we first propose a game model based on the finite Moore automaton, which illustrates the implementation of the model for Niujiu card. At the same time, a novel search strategy combining IMP-minimax and Monte Carlo algorithm is presented in this model. Through the given algorithm, this paper accomplishes the simulation, including not only the process of minimal and optimal occupancy for the first player, but the available frequency of special card type. Experiments show that our model and algorithm are feasible and effective.
목차
1. Introduction
2. Card Game Model
2.1. Composition of Card Game Model
2.2. Controller of Card Game Model
3. Realization of Finite Automaton Based Card Game Model for Niujiu Card
3.1. Formulas and Definition of Niujiu card
3.2. Finite Automaton Based Recognition of Common Cards
3.3. IMP-minimax and Monte Carlo based algorithm recognition of special card type
6. Conclusions
Acknowledgement
References