MWMing-Yan Wang

Ming-Yan Wang

*This is an algorithmically generated author record based on publicly available information.

Ming-Yan Wang has a total of 3 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Research on the Imperfect Information Game of Four-Player Mahjong Based on Mix-PPO

    by Jia-Yang Wang, Ming-Yan Wang, Wang Zeng, Zi-An Zhong

    In recent years, the deep reinforcement learning method has performed well in many challenging tasks, including Go, MOBA games and other industrial fields. Mahjong is a popular game with imperfect information, but because of its large amount of hidden information and complex game rules, it is very challenging to solve its game intelligence decision problem and build AI beyond the human level. To solve the above problems, this paper proposes a feature encoding method and model training strategy for four players in Chinese Mahjong. Additionally, this paper also innovatively proposes the Mix-PPO algorithm, which combines the advantages of the traditional PPO1 algorithm and the PPO2 algorithm, and compares the Mix-PPO algorithm with other algorithms, including the traditional PPO algorithm, the deep learning-related algorithm and the game search tree algorithm. The experimental results show the validity of the feature coding and the Mix-PPO algorithm of Chinese four-player Mahjong in building the decision-making model of Chinese four-player Mahjong, as well as the validity of the coding method of the model's Mahjong feature and the training strategy.