Decentralized Q-Learning for Aggregated Interference Control in Completely and Partially Observable Cognitive Radio Networks.
Ana Galindo-SerranoLorenza GiupponiPublished in: CCNC (2010)
Keyphrases
- cognitive radio networks
- partially observable
- spectrum sensing
- reinforcement learning
- state space
- user centric
- multi agent
- cognitive radio
- decision problems
- partial observability
- markov decision processes
- dec pomdps
- function approximation
- reward function
- partial observations
- optimal control
- infinite horizon
- markov decision problems
- control system
- optimal policy
- reinforcement learning algorithms
- decentralized control
- dynamical systems
- belief state
- heuristic search
- markov chain
- model free