Recursive Least-Squares Temporal Difference With Gradient Correction.
Tianheng SongDazi LiWeimin YangKotaro HirasawaPublished in: IEEE Trans. Cybern. (2021)
Keyphrases
- differential evolution
- temporal difference
- recursive least squares
- gradient method
- step size
- convergence speed
- td learning
- actor critic
- particle swarm optimization
- neuro fuzzy
- evaluation function
- convergence rate
- monte carlo
- policy gradient
- reinforcement learning
- adaptive filtering
- function approximation
- model free
- policy iteration
- reinforcement learning algorithms
- action selection
- learning rate
- cost function
- kalman filtering
- least squares
- wavelet neural network
- complex valued
- pattern recognition
- active learning
- optimization methods
- real valued
- radial basis function
- supervised learning
- image processing