conftrace_

implicit exploration

3 papers

Explore in graph

Co-occurring keywords

regret bound (1926) multi-armed bandit (1098) regret minimization (315) bandit problem (12) delayed feedback (54) high-probability bound (7) side observation (5) high probability regret (2) non-stochastic bandit (1) partial observability (119)

Papers

A Best-of-both-worlds Algorithm for Bandits with Delayed Feedback with Robustness to Excessive Delays NIPS 2024
Explore no more: Improved high-probability regret bounds for non-stochastic bandits NIPS 2015
Efficient learning by implicit exploration in bandit problems with side observations NIPS 2014