Differentially Private Reinforcement Learning with Linear Function Approximation.
Xingyu ZhouPublished in: Proc. ACM Meas. Anal. Comput. Syst. (2022)
Keyphrases
- function approximation
- differentially private
- reinforcement learning
- temporal difference learning algorithms
- function approximators
- temporal difference
- temporal difference learning
- differential privacy
- model free
- reinforcement learning algorithms
- learning tasks
- radial basis function
- learning algorithm
- transfer learning
- privacy preserving
- neural network
- state space
- dynamic programming
- td learning
- machine learning
- optimal policy
- feature extraction
- contingency tables
- e learning