Research map / Bandits and online learning / Multi-armed bandits
Are sample means in multi-armed bandits positively or negatively biased?
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use optimistic sampling with fixed stopping and a fixed target arm | Stochastic MAB sample means · General stochastic MAB | sample-mean bias | Hurt |
| Use optimistic stopping with nonadaptive sampling and choosing | Stochastic MAB sample means · General stochastic MAB | sample-mean bias | Helped |
| Use optimistic choosing with nonadaptive sampling and stopping | Stochastic MAB sample means · General stochastic MAB | sample-mean bias | Helped |
| Combine adaptive optimistic sampling, stopping, and choosing | Stochastic MAB sample means · General stochastic MAB | sample-mean bias | Mixed |
| Use UCB for adaptive sampling until a deterministic horizon | Three unit-variance Gaussian arms · Fixed horizon T = 200 | sample-mean bias | Hurt |
| Use Thompson sampling for adaptive sampling until a deterministic horizon | Three unit-variance Gaussian arms · Fixed horizon T = 200 | sample-mean bias | Hurt |
| Stop at the sequential test boundary for arm 1 | One-sided sequential likelihood ratio test · Null and alternative hypotheses | sample-mean bias | Helped |
| Stop at the sequential test boundary for arm 2 | One-sided sequential likelihood ratio test · Null and alternative hypotheses | sample-mean bias | Hurt |
| Run adaptive sampling, stopping, and choosing together | lil'UCB · Best-arm identification, three Gaussian arms | chosen sample-mean bias | Helped |
Closest papers by meaning
- Simulation-Based Inference for Adaptive Experiments (NeurIPS 2025 · similarity 0.89)
- Balancing Performance and Costs in Best Arm Identification (NeurIPS 2025 · similarity 0.88)
- Best Arm Identification for Stochastic Rising Bandits (ICML 2024 · similarity 0.88)
- On the Asymptotic Optimality of Confidence Interval Based Algorithms for Fixed Confidence MABs (AAAI 2025 · similarity 0.88)
- Robustly Improving Bandit Algorithms with Confounded and Selection Biased Offline Data: A Causal Approach (AAAI 2024 · similarity 0.88)
- Noise-Adaptive Confidence Sets for Linear Bandits and Application to Bayesian Optimization (ICML 2024 · similarity 0.88)
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.