Using Markov decision process in cognitive radio networks towards the optimal reward.
Said LakhalZouhair GuennounPublished in: ICSDE (2017)
Keyphrases
- markov decision process
- stationary policies
- cognitive radio networks
- reinforcement learning
- markov decision processes
- reward function
- state space
- dynamic programming
- finite horizon
- policy iteration
- optimal solution
- spectrum sensing
- channel allocation
- optimal policy
- cognitive radio
- average cost
- average reward
- user centric
- initial state
- machine learning
- multiple agents
- infinite horizon
- finite state