Deep Reinforcement Learning for Auto-optimization of I/O Accelerator Parameters.
Trong-Ton PhamDennis Mintah DjanPublished in: Bench (2019)
Keyphrases
- reinforcement learning
- parameter optimization
- highly non linear
- optimization method
- response surface
- function approximation
- parameter values
- maximum likelihood
- optimization problems
- parameter estimation
- optimization algorithm
- input output
- optimization criteria
- sensitivity analysis
- evolutionary strategy
- machine learning
- probabilistic model
- genetic algorithm
- learning algorithm
- fine tuning
- reinforcement learning algorithms
- action selection
- optimization process
- artificial neural networks
- learning process
- file system
- global optimization
- neural network
- expectation maximization
- evolutionary algorithm