Research map / Bandits and online learning / Multi-armed bandits
Rotting 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 wSWA rather than UCB1 | Non-parametric Rotting Bandits · Non-parametric simulation | end-of-horizon wins: 100 wins | Helped |
| Use wSWA rather than DUCB | Non-parametric Rotting Bandits · Non-parametric simulation | end-of-horizon wins: 100 wins | Helped |
| Use wSWA rather than SWUCB | Non-parametric Rotting Bandits · Non-parametric simulation | end-of-horizon wins: 100 wins | Helped |
| Use CTO rather than UCB1 | Parametric asymptotically vanishing Rotting Bandits · Parametric AV simulation | end-of-horizon wins: 100 wins | Helped |
| Use CTO rather than DUCB | Parametric asymptotically vanishing Rotting Bandits · Parametric AV simulation | end-of-horizon wins: 100 wins | Helped |
| Use CTO rather than SWUCB | Parametric asymptotically vanishing Rotting Bandits · Parametric AV simulation | end-of-horizon wins: 100 wins | Helped |
| Use CTO rather than wSWA | Parametric asymptotically vanishing Rotting Bandits · Parametric AV simulation | end-of-horizon wins: 100 wins | Helped |
| Use D-CTO rather than UCB1 | Parametric asymptotically non-vanishing Rotting Bandits · Parametric ANV simulation | end-of-horizon wins: 100 wins | Helped |
| Use D-CTO rather than DUCB | Parametric asymptotically non-vanishing Rotting Bandits · Parametric ANV simulation | end-of-horizon wins: 100 wins | Helped |
| Use D-CTO rather than SWUCB | Parametric asymptotically non-vanishing Rotting Bandits · Parametric ANV simulation | end-of-horizon wins: 100 wins | Helped |
| Use D-CTO rather than wSWA | Parametric asymptotically non-vanishing Rotting Bandits · Parametric ANV simulation | end-of-horizon wins: 66 wins | Helped |
Closest papers by meaning
- An Adaptive Approach for Infinitely Many-armed Bandits under Generalized Rotting Constraints (NeurIPS 2024 · similarity 0.91)
- On Multi-Armed Bandit with Impatient Arms (ICML 2024 · similarity 0.91)
- Strategic Multi-Armed Bandit Problems Under Debt-Free Reporting (NeurIPS 2024 · similarity 0.89)
- Forced Exploration in Bandit Problems (AAAI 2024 · similarity 0.89)
- Delay as Payoff in MAB (AAAI 2025 · similarity 0.88)
- Tracking Most Significant Shifts in Infinite-Armed Bandits (ICML 2025 · 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.