Research map / Bandits and online learning / Multi-armed bandits
Stochastic bandits with groups of similar arms.
Fabien Pesquerel, Hassan SABER, Odalric-Ambrym Maillard
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 |
|---|---|---|---|
| use IMED-EC (exploit equivalence classes) instead of unstructured IMED/KLUCB/UCB | IMED-EC · Gaussian bandit, balanced classes, known class size | cumulative regret | Improved |
| use IMED-EC instead of OSSB (structured bandit baseline) | IMED-EC · Gaussian bandit, 3 classes x 3 arms | cumulative regret | Improved |
| use only a lower bound q on class size rather than exact size | IMED-EC · Gaussian bandit, 7 classes x 8 arms | cumulative regret | Improved |
| increase q up to the minimal class cardinality (ablation) | IMED-EC · Gaussian bandit, 7 unbalanced classes (4 to 23 arms) | cumulative regret | Improved |
| set q above the true minimal class size (ablation) | IMED-EC · Gaussian bandit, 7 unbalanced classes | mean cumulative regret | No clear effect |
| set q to 7 or 20 (beyond the valid bound) (ablation) | IMED-EC · Gaussian bandit, 7 unbalanced classes | 0.9 quantile of regret | Hurt |
Closest papers by meaning
- Regret Minimisation in Multi-Armed Bandits Using Bounded Arm Memory (AAAI 2020 · similarity 0.92)
- Combinatorial semi-bandit with known covariance (NeurIPS 2016 · similarity 0.91)
- Minimal Exploration in Structured Stochastic Bandits (NeurIPS 2017 · similarity 0.91)
- Bandits with many optimal arms (NeurIPS 2021 · similarity 0.91)
- p-Mean Regret for Stochastic Bandits (AAAI 2025 · similarity 0.90)
- Combinatorial Stochastic-Greedy Bandit (AAAI 2024 · 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.
