Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient.
Ming YinMengdi WangYu-Xiang WangPublished in: ICLR (2023)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference learning
- temporal difference learning algorithms
- temporal difference
- tile coding
- radial basis function
- state action space
- model free
- function approximators
- reinforcement learning algorithms
- mountain car
- dynamic programming
- learning algorithm
- learning tasks
- decision trees
- support vector machine
- td learning
- multi agent