Model-free Q-learning optimal resource allocation in uncertain communication networks.
Gokhan CetinM. Sami FadaliHao XuPublished in: SSCI (2016)
Keyphrases
- model free
- communication networks
- optimal resource allocation
- resource allocation
- reinforcement learning
- reinforcement learning algorithms
- function approximation
- policy iteration
- temporal difference
- distributed databases
- decision making
- computer networks
- network structure
- smart card
- policy evaluation
- state space
- neural network
- data processing
- data model
- average reward
- information systems