High-Probability Sample Complexities for Policy Evaluation With Linear Function Approximation.
Gen LiWeichen WuYuejie ChiCong MaAlessandro RinaldoYuting WeiPublished in: IEEE Trans. Inf. Theory (2024)
Keyphrases
- function approximation
- policy evaluation
- temporal difference
- reinforcement learning
- model free
- function approximators
- td learning
- radial basis function
- semi parametric
- monte carlo
- policy iteration
- variance reduction
- learning tasks
- least squares
- sample size
- linear model
- policy gradient
- state space
- dynamic programming
- learning process
- artificial neural networks
- multi agent