An Improved Best-of-both-worlds Algorithm for Bandits with Delayed Feedback.
Saeed MasoudianJulian ZimmertYevgeny SeldinPublished in: CoRR (2023)
Keyphrases
- improved algorithm
- experimental evaluation
- optimization algorithm
- learning algorithm
- cost function
- dynamic programming
- objective function
- computational complexity
- preprocessing
- significant improvement
- detection algorithm
- np hard
- matching algorithm
- experimental study
- computationally efficient
- high accuracy
- computational cost
- optimal solution
- neural network
- selection algorithm
- estimation algorithm
- classification algorithm
- ant colony optimization
- linear programming
- image processing
- genetic algorithm