Infinite Arms Bandit: Optimality via Confidence Bounds.
Hock Peng ChanShouri HuPublished in: CoRR (2018)
Keyphrases
- confidence bounds
- multi armed bandit problems
- bandit problems
- multi armed bandits
- optimal solution
- random sampling
- multi armed bandit
- exhaustive search
- artificial intelligence
- data mining
- average cost
- optimality criterion
- hidden markov models
- search algorithm
- database systems
- integer linear programming formulation
- computer vision