Research map / Bandits and online learning / Multi-armed bandits
From Finite to Countable-Armed Bandits
Anand Kalvit, Assaf J. Zeevi
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| increase gap Delta from small to large | ALG(UCB1,Theta,2) bound · Monte-Carlo, Bernoulli rewards | beta_Delta | Improved |
| small gap Delta toward 0 | ALG(UCB1,Theta,2) bound · Monte-Carlo, Bernoulli rewards | beta_Delta | Hurt |
| use UCB1 instead of Thompson Sampling in zero-gap two-armed bandit | two-armed bandit with Bernoulli(0.5) arms · fraction of plays of arm 1 at n=10,000 | concentration around 1/2 | Improved |
| use Thompson Sampling with Gaussian priors instead of Beta priors | Thompson Sampling · zero-gap two-armed bandit | distribution of play fraction | Mixed |
| increase UCB exploration parameter rho | UCB(rho) · zero-gap vs well-separated instances | tail of play fraction vs regret | Mixed |
Closest papers by meaning
- Adaptive Algorithms for Infinitely Many-Armed Bandits: A Unified Framework (JMLR 2026 · similarity 0.92)
- Adaptation to the Range in K-Armed Bandits (JMLR 2023 · similarity 0.92)
- A Closer Look at the Worst-case Behavior of Multi-armed Bandit Algorithms (NeurIPS 2021 · similarity 0.91)
- Adaptive Regret for Bandits Made Possible: Two Queries Suffice (ICLR 2024 · similarity 0.90)
- An Adaptive Approach for Infinitely Many-armed Bandits under Generalized Rotting Constraints (NeurIPS 2024 · similarity 0.89)
- Leveraging (Biased) Information: Multi-armed Bandits with Offline Data (ICML 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
