Research map / Bandits and online learning / Multi-armed bandits
Lenient Regret for Multi-Armed Bandits
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 ε-TS instead of vanilla Thompson Sampling | Bernoulli multi-armed bandits · Minimum gap > ε; standard regret | standard regret | Helped |
| Use ε-TS instead of vanilla Thompson Sampling | Bernoulli multi-armed bandits · Optimal mean > 1−ε; lenient regret | lenient regret | Helped |
| Use ε-TS instead of vanilla Thompson Sampling | Bernoulli multi-armed bandits · μ*=0.5, minimum gap < ε; standard regret | standard regret: 20,000 steps | Mixed |
| Use ε-TS instead of vanilla Thompson Sampling | Bernoulli multi-armed bandits · μ*=0.9, minimum gap < ε; standard regret | standard regret | Hurt |
| Use ε-TS instead of vanilla Thompson Sampling | Bernoulli multi-armed bandits · μ*=0.9, minimum gap < ε; lenient regret | lenient regret | Helped |
| Ignore gaps at most ε when defining regret | Stochastic multi-armed bandits · Problems with optimal mean > 1−ε | lenient regret | Helped |
Closest papers by meaning
- A Closer Look at the Worst-case Behavior of Multi-armed Bandit Algorithms (NeurIPS 2021 · similarity 0.92)
- On Regret with Multiple Best Arms (NeurIPS 2020 · similarity 0.92)
- Forced Exploration in Bandit Problems (AAAI 2024 · similarity 0.91)
- Adaptive Regret for Bandits Made Possible: Two Queries Suffice (ICLR 2024 · similarity 0.90)
- Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals (ICML 2024 · similarity 0.90)
- p-Mean Regret for Stochastic Bandits (AAAI 2025 · similarity 0.90)
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.