Research on improving Mahjong model based on deep reinforcement learning.
Yajie WangZhihao WeiShengyu HanZhonghui ShiPublished in: Int. J. Comput. Sci. Math. (2024)
Keyphrases
- reinforcement learning
- model free
- function approximation
- state space
- learning algorithm
- policy search
- markov decision processes
- markov chain
- learning process
- objective function
- multi agent
- dynamic programming
- supervised learning
- data driven
- knowledge base
- artificial intelligence
- machine learning
- databases
- temporal difference
- deep learning
- function approximators
- data sets