Multi-Armed Bandits with Bounded Arm-Memory: Near-Optimal Guarantees for Best-Arm Identification and Regret Minimization

Aug-16-2025, 13:18:58 GMT–Neural Information Processing Systems

We study the Stochastic Multi-armed Bandit problem under bounded arm-memory.

algorithm, cumulative regret, sample complexity, (15 more...)

Neural Information Processing Systems

Aug-16-2025, 13:18:58 GMT

Conferences PDF

Country:
- Asia > India
  - Karnataka > Bengaluru (0.04)
  - West Bengal > Kharagpur (0.04)

Genre:
- Research Report (0.46)

Technology:
- Information Technology
  - Artificial Intelligence > Machine Learning (1.00)
  - Data Science > Data Mining
    - Big Data (1.00)

Duplicate Docs Excel Report

Title
Multi-ArmedBanditswithBoundedArm-Memory: Near-OptimalGuaranteesforBest-Arm IdentificationandRegretMinimization

Similar Docs Excel Report more

Title	Similarity	Source
None found