Exponential Hardness of Reinforcement Learning with Linear Function Approximation.
Sihan LiuGaurav MahajanDaniel KaneShachar LovettGellért WeiszCsaba SzepesváriPublished in: COLT (2023)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference learning algorithms
- function approximators
- temporal difference
- temporal difference learning
- mountain car
- model free
- state action space
- tile coding
- state space
- learning tasks
- radial basis function
- reinforcement learning methods
- dynamic programming
- td learning
- pattern recognition
- temporal difference methods
- policy search
- reinforcement learning problems
- multi agent
- machine learning
- artificial neural networks
- learning algorithm