Learning One Representation to Optimize All Rewards.
Ahmed TouatiYann OllivierPublished in: NeurIPS (2021)
Keyphrases
- learning tasks
- learning process
- learning systems
- learning algorithm
- reinforcement learning
- learning problems
- feature hierarchies
- real time
- learning analytics
- incremental learning
- learning scenarios
- background knowledge
- knowledge acquisition
- online learning
- supervised learning
- prior knowledge
- artificial intelligence