Dynamic Planning and Learning under Recovering Rewards.
David Simchi-LeviZeyu ZhengFeng ZhuPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- decision theoretic
- learning process
- online learning
- domain independent
- learning tasks
- learning scheme
- data sets
- learning algorithm
- prior knowledge
- knowledge acquisition
- unsupervised learning
- learning systems
- control knowledge
- search control rules
- predictive state representations
- learning community
- machine learning
- neural network