Learning to Interrupt: A Hierarchical Deep Reinforcement Learning Framework for Efficient Exploration.
Tingguang LiJin PanDelong ZhuMax Q.-H. MengPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- active learning
- learning systems
- learning mechanism
- learning scheme
- function approximation
- unsupervised learning
- supervised learning
- main contribution
- learning problems
- prior knowledge
- knowledge acquisition
- neural network
- design principles
- probabilistic model
- dynamic bayesian networks
- hierarchical model
- deep learning
- temporal difference learning
- automatically learned
- active exploration