Distributed Reinforcement Learning based MAC protocols for autonomous cognitive secondary users.
Mario BkassinySudharman K. JayaweeraKeith A. AveryPublished in: WOCC (2011)
Keyphrases
- reinforcement learning
- autonomous learning
- cooperative
- multi agent
- information processing
- distributed systems
- machine learning
- end users
- distributed environment
- function approximation
- transparent access
- learning capabilities
- multi party
- user profiles
- user interaction
- social media
- mobile agents
- markov decision processes
- peer to peer
- sensemaking
- multi agent systems
- semantically heterogeneous
- learning algorithm