Cascading Bandits with Noisy Observations: Algorithms and Regret Bounds
arXiv:2610.29381v1 Announce Type: cross Abstract: We propose a novel stochastic cascading bandit setup where probing an ordered shortlist of $K$ out of $L$ arms incurs position-dependent costs, and the learner observes only noisy feedback regarding each arm's true output. We identify a sub-class of…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-22 04:00 · arXiv stat.ML
Cascading Bandits with Noisy Observations: Algorithms and Regret Bounds