Actor-Critic-Based Resource Allocation for Multi-Modal Optical Networks.
Boyuan YanYongli ZhaoYajie LiXiaosong YuJie ZhangYing WangLongchun YanSabidur RahmanPublished in: GLOBECOM Workshops (2018)
Keyphrases
- multi modal
- resource allocation
- optical networks
- actor critic
- reinforcement learning
- optimal control
- policy gradient
- approximate dynamic programming
- temporal difference
- neuro fuzzy
- gradient method
- policy iteration
- reinforcement learning algorithms
- game theory
- function approximation
- resource management
- wireless networks
- average reward
- high dimensional
- step size
- evaluation function
- combinatorial auctions
- optimal policy
- linear program
- fuzzy rules
- sufficient conditions
- linear programming
- least squares
- dynamic programming
- dynamic reconfiguration
- link failure