Distributed Deep Reinforcement Learning with Wideband Sensing for Dynamic Spectrum Access.
Umuralp KaytazSeyhan UcarBaris AkgünSinem ColeriPublished in: WCNC (2020)
Keyphrases
- reinforcement learning
- spectrum sensing
- multi agent
- cooperative
- peer to peer
- learning algorithm
- cognitive radio
- dynamic environments
- distributed environment
- transparent access
- distributed systems
- function approximation
- multiple autonomous
- uniform access
- optimal policy
- computer networks
- fault tolerant
- optimal control
- exchange information
- supervised learning
- scalable distributed
- state space