Bandit Algorithms Comparison Hub
3 papers - avg viability 2.7
Top Papers
- What Do We Care About in Bandits with Noncompliance? BRACE: Bandits with Recommendations, Abstention, and Certified Effects(4.0)
BRACE is a novel algorithm for optimizing recommendations in bandit settings with noncompliance, enhancing treatment learning and uncertainty quantification.
- On The Complexity of Best-Arm Identification in Non-Stationary Linear Bandits(2.0)
This paper explores the complexities of identifying the best arm in non-stationary linear bandits.
- A Reduction Algorithm for Markovian Contextual Linear Bandits(2.0)
This paper presents a theoretical reduction algorithm for Markovian contextual linear bandits.