First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach.
Andrew WagenmakerYifang ChenMax SimchowitzSimon S. DuKevin JamiesonPublished in: CoRR (2021)
Keyphrases
- function approximation
- robust estimation
- reinforcement learning
- function approximators
- temporal difference learning algorithms
- least squares
- temporal difference learning
- model free
- temporal difference
- learning tasks
- reinforcement learning algorithms
- reward function
- motion field
- machine learning
- temporal difference methods
- radial basis function
- td learning
- loss function
- learning algorithm
- neural network
- policy evaluation
- reinforcement learning methods
- state space
- optimal policy
- linear combination