![]() ![]() Finally, we conduct experiments to illustrate the effectiveness of Under each type of adversary, and show that our algorithm is optimal under the Our work presents the first line of robust Lipschitz bandit algorithms that canĪchieve sub-linear regret under both types of adversary, even when the totalīudget of corruption $C$ is unrevealed to the agent. Of the current action before the attack, while the strong one can observe it. ![]() WeĬonsider both weak and strong adversaries, where the weak adversary is unaware ![]() Is measured by the sum of corruption levels across the time horizon $T$. Lipschitz bandits in the presence of adversarial corruptions where an adaptiveĪdversary corrupts the stochastic rewards up to a total budget $C$. In this paper, we introduce a new problem of Download a PDF of the paper titled Robust Lipschitz Bandits to Adversarial Corruptions, by Yue Kang and 2 other authors Download PDF Abstract: Lipschitz bandit is a variant of stochastic bandits that deals with aĬontinuous arm set defined on a metric space, where the reward function is ![]()
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |