Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation.
Pihe HuYu ChenLongbo HuangPublished in: ICML (2022)
Keyphrases
- function approximation
- reinforcement learning
- function approximators
- temporal difference learning algorithms
- temporal difference learning
- temporal difference
- tile coding
- mountain car
- model free
- state action space
- radial basis function
- dynamic programming
- learning tasks
- optimal control
- reinforcement learning algorithms
- machine learning
- control policy
- learning algorithm
- optimal policy
- image classification
- approximate dynamic programming
- genetic algorithm