Ming-Yan Wang
Research Subjects
Ming-Yan Wang has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Jiayang Wang
School of Software, Jiangxi Agricultural University, Nanchang 330045, China
1 shared publication Wang Zeng
School of Information Engineering, Nanchang University, Nanchang, China
1 shared publication- Zi-An Zhong
School of Information Engineering, Nanchang University, Nanchang, China
1 shared publication
Latest Publications
- Open Access
- 4 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 17 (2) , 485-497
Research on the Imperfect Information Game of Four-Player Mahjong Based on Mix-PPO
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.
- 4 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 17 (2) , 485-497
Open AccessResearch on the Imperfect Information Game of Four-Player Mahjong Based on Mix-PPO
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.