On Weak Regret Analysis for Dueling Bandits
–Neural Information Processing Systems
When the optimality gap is negligible, we propose another algorithm that outperforms our first algorithm, highlighting the subtlety of this dueling bandit problem.
Neural Information Processing Systems
Oct-10-2025, 01:12:54 GMT
- Country:
- Europe
- France > Occitanie
- Hérault > Montpellier (0.04)
- Germany > Brandenburg
- Potsdam (0.04)
- France > Occitanie
- North America > United States (0.04)
- Europe
- Genre:
- Research Report > Experimental Study (0.93)
- Industry:
- Leisure & Entertainment (0.45)
- Technology: