Differentially Private Reinforcement Learning with Linear Function Approximation.
Xingyu ZhouPublished in: SIGMETRICS (Abstracts) (2022)
Keyphrases
- function approximation
- differentially private
- reinforcement learning
- function approximators
- temporal difference learning algorithms
- differential privacy
- temporal difference learning
- temporal difference
- learning tasks
- model free
- radial basis function
- reinforcement learning algorithms
- state space
- learning algorithm
- supervised learning
- dynamic programming
- neural network
- artificial neural networks
- td learning
- temporal difference methods