Proposes e RCDP-UCB algorithm achieving regret bound ŵO(d(√T + C + D)) for linear dueling bandits under post-serving contexts, delays, and corruptions with additive corruption-delay cost.
Nearly optimal algorithms for con- textual dueling bandits from adversarial feedback.arXiv preprint arXiv:2404.10776
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Robust Linear Dueling Bandits with Post-serving Context under Unknown Delays and Adversarial Corruptions
Proposes e RCDP-UCB algorithm achieving regret bound ŵO(d(√T + C + D)) for linear dueling bandits under post-serving contexts, delays, and corruptions with additive corruption-delay cost.