FORLORN: A Framework for Comparing Offline Methods and Reinforcement Learning for Optimization of RAN Parameters.
Vegard EdvardsenGard SpreemannJeriek Van den AbeelePublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- learning algorithm
- significant improvement
- benchmark datasets
- preprocessing
- computational cost
- optimization methods
- maximum likelihood
- global optimization
- concave convex procedure
- neural network
- fine tuning
- control problems
- machine learning methods
- optimization algorithm
- optimization problems
- state space
- multi objective
- decision trees