Exponential Hardness of Reinforcement Learning with Linear Function Approximation.
Daniel KaneSihan LiuShachar LovettGaurav MahajanCsaba SzepesváriGellért WeiszPublished in: CoRR (2023)
Keyphrases
- function approximation
- reinforcement learning
- function approximators
- temporal difference learning algorithms
- temporal difference
- temporal difference learning
- tile coding
- learning tasks
- mountain car
- state action space
- model free
- td learning
- learning algorithm
- radial basis function
- reinforcement learning algorithms
- multi agent
- reinforcement learning problems
- markov decision processes
- state space
- temporal difference methods
- action space
- reinforcement learning methods
- machine learning