On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation.
Thanh Nguyen-TangMing YinSunil GuptaSvetha VenkateshRaman AroraPublished in: CoRR (2022)
Keyphrases
- function approximation
- reinforcement learning
- function approximators
- temporal difference learning algorithms
- temporal difference
- temporal difference learning
- model free
- radial basis function
- mountain car
- tile coding
- state action space
- learning tasks
- reinforcement learning algorithms
- dynamic programming
- state space
- td learning
- markov decision processes
- supervised learning
- semi supervised
- policy iteration
- learning process