Improved Regret for Efficient Online Reinforcement Learning with Linear Function Approximation.
Uri ShermanTomer KorenYishay MansourPublished in: ICML (2023)
Keyphrases
- function approximation
- reinforcement learning
- function approximators
- temporal difference learning algorithms
- temporal difference learning
- online learning
- model free
- temporal difference
- learning tasks
- radial basis function
- mountain car
- state space
- reinforcement learning algorithms
- learning algorithm
- active learning
- neural network
- td learning
- policy evaluation
- exploration exploitation tradeoff
- policy gradient
- reward function
- least squares
- learning process
- e learning
- genetic algorithm
- machine learning