Building a 3-Player Mahjong AI using Deep Reinforcement Learning.
Xiangyu ZhaoSean B. HoldenPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- artificial intelligence
- state space
- machine learning
- intelligent systems
- john mccarthy
- optimal control
- function approximation
- optimal policy
- knowledge based systems
- learning process
- dynamic programming
- learning problems
- expert systems
- model free
- reinforcement learning algorithms
- deep learning
- neural network