Revisiting the Linear-Programming Framework for Offline RL with General Function Approximation.
Asuman E. OzdaglarSarath PattathilJiawei ZhangKaiqing ZhangPublished in: CoRR (2022)
Keyphrases
- function approximation
- reinforcement learning
- linear programming
- temporal difference
- radial basis function
- model free
- neural network
- temporal difference learning algorithms
- temporal difference learning
- function approximators
- pattern recognition
- machine learning
- policy search methods
- tile coding
- dynamic programming
- text classification
- image classification
- state space
- feature extraction
- learning algorithm