A Generalized Stacked Reinforcement Learning Method for Sampled Systems.
Pavel OsinenkoDmitrii DobriborsciGrigory YaremenkoGeorgiy MalaniyaPublished in: IEEE Trans. Autom. Control. (2023)
Keyphrases
- reinforcement learning
- preprocessing
- cost function
- high precision
- mathematical model
- experimental evaluation
- detection method
- classification accuracy
- complex systems
- synthetic data
- least squares
- significant improvement
- similarity measure
- image registration
- probabilistic model
- high accuracy
- computationally efficient
- optimization algorithm
- computational cost
- mobile robot
- color images
- pairwise
- optimization method