A Slice Admission Policy Based on Reinforcement Learning for a 5G Flexible RAN.
M. R. RazaCarlos NatalinoPeter OhlenLena WosinskaPaolo MontiPublished in: ECOC (2018)
Keyphrases
- reinforcement learning
- optimal policy
- admission control
- policy search
- markov decision process
- action selection
- control policy
- partially observable environments
- state and action spaces
- action space
- function approximators
- function approximation
- policy gradient
- policy iteration
- control policies
- state action
- end to end
- state space
- reinforcement learning algorithms
- reinforcement learning problems
- approximate dynamic programming
- actor critic
- asymptotic optimality
- model free reinforcement learning
- machine learning
- model free
- infinite horizon
- multi agent
- decision problems
- finite state
- asymptotically optimal
- continuous state
- markov decision problems
- temporal difference
- partially observable
- control problems
- reinforcement learning methods
- learning classifier systems
- reward function
- lightweight
- markov chain
- learning process
- partially observable domains