Small cell switch policy: A reinforcement learning approach.
Luyang WangXinxin FengXiaoying GanJing LiuHui YuPublished in: WCSP (2014)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- action selection
- markov decision process
- high speed
- machine learning
- action space
- partially observable
- reinforcement learning algorithms
- function approximation
- markov decision processes
- small number
- state space
- control policy
- partially observable environments
- state and action spaces
- reinforcement learning problems
- policy gradient
- neural network
- actor critic
- model free reinforcement learning
- reward function
- policy evaluation
- policy making
- continuous state
- control policies
- function approximators