Suphx: Mastering Mahjong with Deep Reinforcement Learning.
Junjie LiSotetsu KoyamadaQiwei YeGuoqing LiuChao WangRuihan YangLi ZhaoTao QinTie-Yan LiuHsiao-Wuen HonPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- learning algorithm
- function approximation
- model free
- state space
- robotic control
- optimal policy
- partially observable
- coverage includes
- multi agent
- temporal difference
- reinforcement learning algorithms
- database programming
- learning agents
- reinforcement learning methods
- stochastic approximation
- learning problems
- database
- data model
- control problems
- markov decision process
- least squares
- artificial neural networks