Gradient-Based Discrete-Time Concurrent Learning for Standalone Function Approximation.
Ouboti Djaneye-BoundjouRaúl OrdóñezPublished in: IEEE Trans. Autom. Control. (2020)
Keyphrases
- function approximation
- reinforcement learning
- learning tasks
- temporal difference learning
- function approximators
- learning algorithm
- learning process
- temporal difference methods
- active learning
- model free
- temporal difference
- td learning
- learning experience
- evaluation function
- supervised learning
- machine learning
- neural network