Distributionally Robust Off-Dynamics Reinforcement Learning: Provable Efficiency with Linear Function Approximation.
Zhishuai LiuPan XuPublished in: AISTATS (2024)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference learning algorithms
- function approximators
- temporal difference
- tile coding
- temporal difference learning
- mountain car
- model free
- reinforcement learning algorithms
- robust optimization
- state action space
- radial basis function
- neural network
- state space
- exploration exploitation tradeoff
- policy evaluation
- action selection
- transfer learning
- supervised learning
- multi agent
- data mining