Machine game card playing method and system for Guan dan pokers and storage medium

Abstract

The invention relates to a machine game card playing method and system for Guan dan pokers and a storage medium and belongs to the technical field of deep learning and machine game. According to the method, firstly, energy of the faces of drawn cards is calculated; calculation is performed according to an energy calculation formula; cards are divided into three basic effective card patterns; cards are distributed; the faces of the cards are calculated; parameters are trained through deep learning; a formula is obtained by using a minimum data set; parameters are obtained; values are calculated; card playing strategies are adjusted in real time according to the values, the rules of playing cards are divided into three types, including playing cards, following cards and sprint. According to the calculation strategy based on deep learning, a machine algorithm is realized in a poker game, the same method and two groups of algorithms are adopted for two roles of opponents to perform a poker game competition, and finally, a more intelligent poker competition method is trained.

Description

technical field [0001] The present invention relates to the technical fields of deep learning and machine games, and in particular, relates to a method, system and storage medium for playing poker by machines. Background technique [0002] Since the 1940s, Deep Blue and AlphaGo have attracted the attention of the whole people, and machine games have always been a touchstone for verifying computing theory and artificial intelligence theory. Computer game is an important platform for testing the level of artificial intelligence. It is a discipline that researches and develops methods, technologies and applications for simulating, extending and expanding human intelligence theory (references: Yang Shanlin, Ni Zhiwei. Machine Learning and Intelligence Decision support system [M]. Ke xue chu ban she, 2004.), machine game is known as the fruit fly of artificial intelligence (reference: Xu Yanhong. Human-machine game [J]. Art and Design, 2016(4): 150 -151.), similar to the role of...

AI Technical Summary

Problems solved by technology

[0005] The traditional calculation method of poker cards exists: it requires a large memory space, the calculation of card types is not intelligent enough, and the way of matching cards requires a combination of depth traversal and breadth traversal. Every time a card is played, there are problems such as a long time to play cards and lack of versatility.

Images