In stochastic multi-armed bandits with both reward and dueling feedback, the authors prove a regret lower bound and give an algorithm whose regret matches it up to a constant under a common dueling assumption.
Bandits games and clustering foundations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Fusing Reward and Dueling Feedback in Stochastic Bandits
In stochastic multi-armed bandits with both reward and dueling feedback, the authors prove a regret lower bound and give an algorithm whose regret matches it up to a constant under a common dueling assumption.