Abstract | ||
---|---|---|
We investigate the adversarial bandit problem with multiple plays under semi-bandit feedback. We introduce a highly efficient algorithm that asymptotically achieves the performance of the best switching m-arm strategy with minimax optimal regret bounds. To construct our algorithm, we introduce a new expert advice algorithm for the multiple-play setting. By using our expert advice algorithm, we add... |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/TSP.2019.2928952 | IEEE Transactions on Signal Processing |
Keywords | Field | DocType |
Signal processing algorithms,Switches,Games,Time complexity,Performance gain,Computational modeling | Mathematical optimization,Minimax,Regret,Algorithm,Time complexity,Statistical assumption,Mathematics,Signal processing algorithms,Adversarial system | Journal |
Volume | Issue | ISSN |
67 | 16 | 1053-587X |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nuri Mert Vural | 1 | 0 | 0.34 |
Hakan Gokcesu | 2 | 0 | 1.69 |
Kaan Gokcesu | 3 | 8 | 5.26 |
Suleyman Serdar Kozat | 4 | 121 | 31.32 |