task · first seen 19 Oct 2026
non-stationary bandits
Multi-armed bandit problems where reward distributions change over time, requiring adaptation to changes.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Detection Augmented Learning In Non-Stationary Bandit EnvironmentsPapers · 19 Oct 2026 · Argyrios Gerogiannis, Yu-Han Huang, Subhonmesh Bose, Venugopal V. Veeravalli
Latest sources
- Detection Augmented Learning In Non-Stationary Bandit EnvironmentsPapers · 19 Oct 2026 · Argyrios Gerogiannis, Yu-Han Huang, Subhonmesh Bose, Venugopal V. Veeravalli