Hellinger KL-UCB based Bandit Algorithms for Markovian and i.i.d. Settings.
Arghyadip RoySanjay ShakkottaiR. SrikantPublished in: CoRR (2020)
Keyphrases
- bandit problems
- multi armed bandit
- learning algorithm
- data structure
- recently developed
- computationally efficient
- distance measure
- kullback leibler
- computational efficiency
- machine learning algorithms
- data sets
- orders of magnitude
- data mining techniques
- significant improvement
- decision trees
- feature selection
- machine learning