Historical Best Q-Networks for Deep Reinforcement Learning.
Wenwu YuRui WangRuiying LiJing GaoXiaohui HuPublished in: ICTAI (2018)
Keyphrases
- reinforcement learning
- model free
- historical data
- state space
- reinforcement learning algorithms
- social networks
- function approximation
- network structure
- control policy
- network design
- learning problems
- dynamic programming
- case study
- machine learning
- supervised learning
- information systems
- cellular networks
- markov decision process
- neural network