Bandits with Abstention under Expert Advice

S Pasteris, A Rumi, M Thiessen, S Saito… - arxiv preprint arxiv …, 2024 - arxiv.org
We study the classic problem of prediction with expert advice under bandit feedback. Our
model assumes that one action, corresponding to the learner's abstention from play, has no …

A hierarchical nearest neighbour approach to contextual bandits

S Pasteris, C Hicks, V Mavroudis - arxiv preprint arxiv:2312.09332, 2023 - arxiv.org
In this paper we consider the adversarial contextual bandit problem in metric spaces. The
paper" Nearest neighbour with bandit feedback" tackled this problem but when there are …