What can online reinforcement learning with function approximation benefit from general coverage conditions?
Fanghui LiuLuca VianoVolkan CevherPublished in: ICML (2023)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference
- temporal difference learning
- function approximators
- state action space
- tile coding
- radial basis function
- temporal difference learning algorithms
- mountain car
- learning tasks
- model free
- reinforcement learning algorithms
- learning algorithm
- td learning
- state space
- machine learning
- continuous state
- exploration exploitation tradeoff
- evaluation function
- reinforcement learning problems
- optimal policy
- sufficient conditions
- temporal difference methods
- learning process