Refined Algorithms for Infinitely Many-Armed Bandits with Deterministic Rewards.
Yahel DavidNahum ShimkinPublished in: ECML/PKDD (1) (2015)
Keyphrases
- learning algorithm
- reinforcement learning
- computationally efficient
- black box
- computationally expensive
- randomized algorithms
- evolutionary algorithm
- optimization problems
- multi armed bandits
- database
- graph theory
- times faster
- machine learning algorithms
- data mining techniques
- worst case
- query processing
- computational complexity
- objective function
- social networks
- real time