A Deep Double-Q Learning-based Scheme for Anti-Jamming Communications.
Ha Phan Khanh NguyenViet Hung NguyenVan Long DoPublished in: EUSIPCO (2020)
Keyphrases
- cooperative
- communication systems
- real time
- recognition scheme
- function approximation
- multi agent
- state space
- neural network
- communication networks
- reinforcement learning
- learning algorithm
- computational complexity
- video sequences
- optimal policy
- image sequences
- information systems
- network management
- detection scheme
- stochastic approximation