Learning non-myopically from human-generated reward.
W. Bradley KnoxPeter StonePublished in: IUI (2013)
Keyphrases
- reinforcement learning
- learning algorithm
- learning process
- human generated
- learning problems
- learning tasks
- data mining
- online learning
- real time
- supervised learning
- knowledge acquisition
- active learning
- prior knowledge
- learning scenarios
- incremental learning
- learning analytics
- learning scheme
- solving problems
- learning phase