Research map / Bandits and online learning / Multi-armed bandits
Non-Stationary Bandits under Recharging Payoffs: Improved Planning with Sublinear Regret
Orestis Papadigenopoulos, Constantine Caramanis, Sanjay Shakkottai
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 LP rounding and interleaved scheduling for planning | k-RB · k-RB planning | approximation ratio: 1 - k^k/(e^k k!) | Improved |
| Use Randomize-Then-Interleave rather than the prior planning algorithm | 1-RB planning · 1-RB | approximation ratio: 0.25 -> 0.63 | Improved |
| Use Randomize-Then-Interleave rather than the prior planning algorithm | 2-RB planning · 2-RB | approximation ratio: 0.33 -> 0.72 | Improved |
| Use Randomize-Then-Interleave rather than the prior planning algorithm | 3-RB planning · 3-RB | approximation ratio: 0.40 -> 0.77 | Improved |
| Use Randomize-Then-Interleave rather than the prior planning algorithm | 4-RB planning · 4-RB | approximation ratio: 0.44 -> 0.80 | Improved |
| Use Randomize-Then-Interleave rather than the prior planning algorithm | 5-RB planning · 5-RB | approximation ratio: 0.46 -> 0.82 | Improved |
| Use Randomize-Then-Interleave rather than the prior planning algorithm | 10-RB planning · 10-RB | approximation ratio: 0.57 -> 0.87 | Improved |
Closest papers by meaning
- Stochastic Bandits with Graph Feedback in Non-Stationary Environments (AAAI 2021 · similarity 0.91)
- Constrained Feedback Learning for Non-Stationary Multi-Armed Bandits (NeurIPS 2025 · similarity 0.90)
- Non-stationary Bandit Convex Optimization: A Comprehensive Study (NeurIPS 2025 · similarity 0.90)
- p-Mean Regret for Stochastic Bandits (AAAI 2025 · similarity 0.89)
- Contextual Linear Bandits with Delay as Payoff (ICML 2025 · similarity 0.89)
- Nash Social Welfare for Multi Armed Bandits: Trajectory-wise Expected and High Probability Regret (NeurIPS 2026 · similarity 0.89)
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.
