Finding Optimal Arms in Non-stochastic Combinatorial Bandits with Semi-bandit Feedback and Finite Budget. (arXiv:2202.04487v2 [cs.LG] UPDATED)

We consider the combinatorial bandits problem with semi-bandit feedback under
finite sampling budget constraints, in which the learner can carry out its
action only for a limited number of times specified by an overall budget. The
action is to choose a set of arms, whereupon feedback for each arm in the
chosen set is received. Unlike existing works, we study this problem in a
non-stochastic setting with subset-dependent feedback, i.e., the semi-bandit
feedback received could be generated by an oblivious …

arxiv budget feedback stochastic