Reinforcement Learning-Based Joint Self-Optimisation Method for the Fuzzy Logic Handover Algorithm in 5G HetNets.
Qianyu LiuChiew Foong KwongSun WeiLincan LiJing WangPublished in: CoRR (2020)
Keyphrases
- dynamic programming
- cost function
- computational cost
- optimization algorithm
- preprocessing
- clustering method
- experimental evaluation
- improved algorithm
- model free
- detection algorithm
- high accuracy
- computationally efficient
- objective function
- detection method
- segmentation algorithm
- theoretical analysis
- matching algorithm
- computational complexity
- recognition algorithm
- reinforcement learning
- significant improvement
- estimation algorithm
- segmentation method
- fuzzy logic
- optimization method
- classification algorithm
- mathematical model
- synthetic and real images
- genetic algorithm
- neural network
- k means
- fitted q iteration
- input data
- probabilistic model
- selection algorithm
- convergence rate
- reconstruction method
- learning algorithm
- similarity measure
- classification method
- multi objective
- np hard
- support vector machine
- policy search
- function approximators
- weight vector
- global optimisation
- expert systems
- decision trees
- support vector machine svm
- wireless networks
- simulated annealing
- expectation maximization