Abstract | ||
---|---|---|
We propose an online algorithm for sequential learning in the contextual multiarmed bandit setting. Our approach is to partition the context space and, then, optimally combine all of the possible mappings between the partition regions and the set of bandit arms in a data-driven manner. We show that in our approach, the best mapping is able to approximate the best arm selection policy to any desire... |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/TNNLS.2018.2854796 | IEEE Transactions on Neural Networks and Learning Systems |
Keywords | Field | DocType |
Partitioning algorithms,Computational complexity,Upper bound,Convergence,Art,Data models,Learning systems | Online algorithm,Computer science,Upper and lower bounds,Algorithm,Binary tree,Asymptotically optimal algorithm,Statistical assumption,Computational complexity theory,Scalability,Multiclass classification | Journal |
Volume | Issue | ISSN |
30 | 3 | 2162-237X |
Citations | PageRank | References |
0 | 0.34 | 15 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mohammadreza Mohaghegh Neyshabouri | 1 | 1 | 1.70 |
Kaan Gokcesu | 2 | 8 | 5.26 |
Hakan Gokcesu | 3 | 0 | 1.69 |
Huseyin Ozkan | 4 | 40 | 10.44 |
Suleyman Serdar Kozat | 5 | 121 | 31.32 |