Optimal Learning for Structured Bandits.
Bart P. G. Van ParysNegin GolrezaeiPublished in: CoRR (2020)
Keyphrases
- learning problems
- reinforcement learning
- learning process
- online learning
- learning systems
- supervised learning
- learning algorithm
- learning tasks
- mobile devices
- real world
- dynamic programming
- prior knowledge
- inductive learning
- hidden markov models
- active learning
- optimal solution
- case study
- information systems
- genetic algorithm