Research map / Bandits and online learning / Multi-armed bandits
Multi-armed Bandit Requiring Monotone Arm Sequences
Ningyuan Chen
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 |
|---|---|---|---|
| Require the arm sequence to be monotone | Continuum-armed bandit with continuous objectives · General continuous objective | regret: T/4 | Hurt |
| Add the monotonicity constraint to classic UCB | UCB · Simulated unimodal instances | average regret | Hurt |
| Deflate the initial UCB values of unvisited arms to 1-k/K | UCB with monotone arms · Simulated unimodal instances | average regret | Improved |
| Remove the monotonicity constraint | Continuum-armed bandit · Simulated unimodal instances | average regret | Improved |
Closest papers by meaning
- Dynamic Pricing with Monotonicity Constraint under Unknown Parametric Demand Model (NeurIPS 2022 · similarity 0.88)
- Finite Continuum-Armed Bandits (NeurIPS 2020 · similarity 0.87)
- Combinatorial Bandits for Maximum Value Reward Function under Value-Index Feedback (ICLR 2024 · similarity 0.86)
- Forced Exploration in Bandit Problems (AAAI 2024 · similarity 0.85)
- Uncoupled and Convergent Learning in Monotone Games under Bandit Feedback (NeurIPS 2025 · similarity 0.85)
- Nash Social Welfare for Multi Armed Bandits: Trajectory-wise Expected and High Probability Regret (NeurIPS 2026 · similarity 0.85)
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.
