An Online Minimax Optimal Algorithm for Adversarial Multiarmed Bandit Problem.
Kaan GökcesuSuleyman Serdar KozatPublished in: IEEE Trans. Neural Networks Learn. Syst. (2018)
Keyphrases
- dynamic programming
- worst case
- optimal solution
- experimental evaluation
- cost function
- matching algorithm
- detection algorithm
- improved algorithm
- significant improvement
- probabilistic model
- computational cost
- optimization algorithm
- preprocessing
- exhaustive search
- learning algorithm
- real time
- expectation maximization
- linear programming
- np hard
- evolutionary algorithm
- evaluation function
- online algorithms
- convergence rate
- path planning
- particle swarm optimization
- k means
- objective function
- genetic algorithm