An index-based deterministic convergent optimal algorithm for constrained multi-armed bandit problems.
Hyeong Soo ChangPublished in: Autom. (2021)
Keyphrases
- dynamic programming
- learning algorithm
- optimal solution
- worst case
- globally optimal
- computational complexity
- cost function
- objective function
- segmentation algorithm
- expectation maximization
- optimal strategy
- optimization algorithm
- special case
- k means
- preprocessing
- np hard
- simulated annealing
- genetic algorithm
- neural network