A generalized stacked reinforcement learning method for sampled systems.
Pavel OsinenkoDmitrii DobriborsciPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- cost function
- detection method
- pairwise
- optimization method
- high precision
- high accuracy
- significant improvement
- computational cost
- support vector machine
- preprocessing
- mathematical model
- computational complexity
- management system
- evolutionary algorithm
- computer systems
- computationally efficient
- clustering method
- synthetic data
- classification method
- learning algorithm