Learning When and Where to Zoom With Deep Reinforcement Learning.
Burak UzkentStefano ErmonPublished in: CVPR (2020)
Keyphrases
- reinforcement learning
- learning algorithm
- learning process
- temporal difference learning
- learning problems
- learning systems
- inverse reinforcement learning
- machine learning
- learning tasks
- supervised learning
- knowledge acquisition
- mobile learning
- markov decision processes
- online learning
- learning scenarios
- learning agent
- function approximators
- learning agents
- active learning
- evolutionary learning
- prior knowledge