Scaling Life-long Off-policy Learning
Adam WhiteJoseph ModayilRichard S. SuttonPublished in: CoRR (2012)
Keyphrases
- learning algorithm
- life long
- learning process
- unsupervised learning
- learning systems
- multi agent
- learning problems
- online learning
- data sets
- bayesian networks
- inductive inference
- learning scenarios
- learning tasks
- mobile learning
- background knowledge
- low cost
- supervised learning
- software engineering
- end users
- information systems
- reinforcement learning