Maximin action identification: a new bandit framework for games
Presented at the Conference on Learning Theory (June 2016), New York, NY, USA
|V. Feldman , A. Rakhlin (Alexander)|
|Machine Learning at the Intrinsic Task Pace|
|Conference on Learning Theory|
|This work was funded by the The Netherlands Organisation for Scientific Research (NWO); grant id nwo/639.021.439 - Machine Learning at the Intrinsic Task Pace|
|Organisation||Algorithms and Complexity|
Garivier, A, Kaufmann, E, & Koolen-Wijkstra, W.M. (2016). Maximin action identification: a new bandit framework for games. In V Feldman & A Rakhlin (Eds.), JMLR: Workshop and Conference Proceedings (pp. 1028–1050).