Uplink NOMA-based long-term throughput maximization scheme for cognitive radio networks: an actor-critic reinforcement learning approach.
Hoang Thi Huong GiangTran Nhut Khai HoanInsoo KooPublished in: Wirel. Networks (2021)
Keyphrases
- actor critic
- reinforcement learning
- cognitive radio networks
- temporal difference
- policy gradient
- reinforcement learning algorithms
- function approximation
- optimal control
- approximate dynamic programming
- user centric
- traffic load
- neuro fuzzy
- spectrum sensing
- gradient method
- response time
- policy iteration
- cross layer
- multi agent
- application layer
- power allocation
- markov decision processes
- average reward
- model free
- cognitive radio
- state space
- learning algorithm
- supervised learning
- objective function
- machine learning
- optimal policy
- neural network