A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation.
Heyang ZhaoJiafan HeQuanquan GuPublished in: CoRR (2023)
Keyphrases
- function approximation
- reinforcement learning
- dynamic programming
- mountain car
- function approximators
- model free
- temporal difference learning
- td learning
- learning algorithm
- radial basis function
- temporal difference learning algorithms
- policy gradient
- temporal difference
- support vector machine svm
- data mining
- optimal control
- supervised learning
- reinforcement learning algorithms
- state space
- learning process
- search space
- actor critic
- optimal solution
- feature extraction
- machine learning