Provably Efficient High-Dimensional Bandit Learning with Batched Feedbacks.
Jianqing FanZhaoran WangZhuoran YangChenlu YePublished in: CoRR (2023)
Keyphrases
- learning algorithm
- high dimensional
- learning problems
- reinforcement learning
- multi agent
- learning process
- supervised learning
- active learning
- online learning
- background knowledge
- low dimensional
- learning community
- incremental learning
- high dimensionality
- learning tasks
- learning systems
- empirical studies
- state space
- lower bound
- e learning