mlsanityData to 14 Oct 2026

Bounded Regret for Finite-Armed Structured Bandits

arXiv 1411.2919 ↗First posted 11 Nov 2014cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

We study a new type of K-armed bandit problem where the expected return of one arm may depend on the returns of other arms. We present a new algorithm for this general class of problems and show that under certain circumstances it is possible to achieve finite expected cumulative regret. We also give problem-dependent lower bounds on the cumulative regret showing that at least in special cases the new algorithm is nearly optimal.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). First posted on arXiv 11 Nov 2014.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 6; 2022: 2; 2023: 2; 2024: 3; 2025: 1; 2026: 1.

15 papers.

Sort:

By area:

  1. 2021Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learningcited by 66
  2. 2022Deep Hierarchy in Banditscited by 19
  3. 2022Mixed-Effect Thompson Samplingcited by 14
  4. 2021Best-Arm Identification in Correlated Multi-Armed Banditscited by 8
  5. 2023Thompson Sampling with Diffusion Generative Priorcited by 7
  6. 2021Thompson Sampling for Bandits with Clustered Armscited by 6
  7. 2024Causally Abstracted Multi-armed Banditscited by 6
  8. 2024Experiment Planning with Function Approximationcited by 5
  9. 2024Diffusion Models Meet Contextual Banditscited by 5
  10. 2023Quantum contextual bandits and recommender systems for quantum datacited by 4
  11. 2021Bad-Policy Density: A Measure of Reinforcement Learning Hardnesscited by 2
  12. 2021Best Arm Identification under Additive Transfer Banditscited by 1
3 more
  1. 2025A Classification View on Meta Learning Banditscited by 1
  2. 2021TSEC: a framework for online experimentation under experimental constraintscited by 0
  3. 2026Latent Order Banditscited by 0