Research map / Bandits and online learning / Multi-armed bandits
Networked Restless Bandits with Positive Externalities
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 Greta instead of Myopic | Networked restless bandit allocation · Synthetic cohort, random mapping | Intervention benefit (%): 87.83 ~± 1.115 -> 100.00 ~± 0.000 | Helped |
| Use Greta instead of Myopic | Networked restless bandit allocation · Synthetic cohort, by-cluster mapping | Intervention benefit (%): 76.24 ~± 0.921 -> 100.00 ~± 0.000 | Helped |
| Increase message cost | Greta · Synthetic cohort, varied message cost | Expected cumulative reward | Hurt |
| Set message cost to zero rather than a positive value | Greta · Synthetic cohort, varied message cost | Expected cumulative reward | Helped |
| Increase budget | Greta · Synthetic cohort, varied budget | Expected cumulative reward | Helped |
| Increase edge count in the graph | Greta · Synthetic cohort, varied graph topology | Expected cumulative reward | Mixed |
| Increase graph assortativity | Greta · Synthetic cohort, varied graph topology | Expected cumulative reward | Mixed |
| Increase graph disassortativity | Greta · Synthetic cohort, varied graph topology | Expected cumulative reward | Helped |
| Allow message actions alongside pulls rather than using graph-agnostic Threshold Whittle | Greta · Networked restless bandit setting | Expected cumulative reward | Helped |
Closest papers by meaning
- Graph-Triggered Rising Bandits (ICML 2024 · similarity 0.89)
- Global Rewards in Restless Multi-Armed Bandits (NeurIPS 2024 · similarity 0.88)
- Reinforcement learning with combinatorial actions for coupled restless bandits (ICLR 2025 · similarity 0.88)
- The Bandit Whisperer: Communication Learning for Restless Bandits (AAAI 2025 · similarity 0.87)
- Provably Efficient Reinforcement Learning for Adversarial Restless Multi-Armed Bandits with Unknown Transitions and Bandit Feedback (ICML 2024 · similarity 0.86)
- Achieving $\tilde{\mathcal{O}}(1/N)$ Optimality Gap in Restless Bandits through Gaussian Approximation (NeurIPS 2025 · similarity 0.86)
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.