현상
다중무장 밴딧
6편 · 2023 2편, 2024 2편, 2025 1편, 2026 1편
- Speed Up the Cold-Start Learning in Two-Sided Bandits with Many Arms
- Bridging Adversarial and Nonstationary Multi-Armed Bandit
- Thompson Sampling with Information Relaxation Penalties
- Maximal Objectives in the Multiarmed Bandit with Applications
- Phase Transitions in Bandits with Switching Constraints
- A Heuristic Approach to Explore: The Value of Perfect Information