Contextual Bandits with Cross-Learning

Santiago Balseiro, Negin Golrezaei, Mohammad Mahdian, Vahab Mirrokni, Jon Schneider

Neural Information Processing Systems 

In the classical contextual bandits problem, in each roundt, a learner observes some contextc, chooses some actiona to perform, and receives some reward ra,t(c).

Similar Docs  Excel Report  more

TitleSimilaritySource
None found