← Search

Abhishek Kumar Umrawal

2 accepted papers

2022

An explore-then-commit algorithm for submodular maximization under full-bandit feedback

UAI 2022poster

We investigate the problem of combinatorial multi-armed bandits with stochastic submodular (in expectation) rewards and full-bandit feedback, where no extra information other than the reward of selected action at each time step $t$ is observed. We propose a simple algorithm, Explore-Then-Commit Gree…

Cited by 24SourcePDFScholar
2021

DART: Adaptive Accept Reject Algorithm for Non-Linear Combinatorial Bandits

AAAI 2021technical

We consider the bandit problem of selecting K out of N arms at each time step. The joint reward can be a non-linear function of the rewards of the selected individual arms. The direct use of a multi-armed bandit algorithm requires choosing among all possible combinations, making the action space lar…

Cited by 11SourcePDFScholar