Differentially Private Temporal Difference Learning with Stochastic Nonconvex-Strongly-Concave Optimization.
Canzhe ZhaoYanjie ZeJing DongBaoxiang WangShuai LiPublished in: WSDM (2023)
Keyphrases
- temporal difference learning
- differentially private
- global optimization
- evaluation function
- objective function
- function approximation
- reinforcement learning
- monte carlo
- fixed point
- game playing
- temporal difference
- differential privacy
- markov chain
- data sets
- reinforcement learning algorithms
- markov decision process