Near-optimal Representation Learning for Linear Bandits and Linear RL.
Jiachen HuXiaoyu ChenChi JinLihong LiLiwei WangPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- machine learning
- autonomous learning
- learning tasks
- closed form
- knowledge acquisition
- active learning
- learning systems
- prior knowledge
- linear systems
- function approximators
- learning agents
- supervised learning
- state space
- background knowledge
- learned knowledge
- temporal difference learning
- reinforcement learning methods
- multi agent