Exploration via Feature Perturbation in Contextual Bandits
NeurIPSSpotlight2025
TL;DR
We propose *feature perturbation*, a simple yet effective exploration strategy for contextual bandits that injects randomness directly into feature inputs, instead of randomizing unknown parameters or…
Opening excerpt from the authors’ abstract. source
Read the paper
Topics
exploration bandit
← All NeurIPS 2025 Spotlight papers · Browse the whole archive