Research map / Bandits and online learning / Multi-armed bandits
Cooperative Multi-Agent Bandits with Heavy Tails
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 robust mean estimation and message passing instead of empirical-mean running consensus | Cooperative multi-agent bandits · Random Erdos-Renyi and Barabasi-Albert graphs | group regret | Helped |
| Increase communication density γ (ablation) | MP-UCB · Random Erdos-Renyi graphs | group regret | Helped |
| Increase communication density γ (ablation) | KMP-UCB · Random Erdos-Renyi graphs | group regret | No clear effect |
| Make the reward tails heavier by moving α toward 1 (ablation) | Consensus-UCB · Random Erdos-Renyi graphs | group regret | Hurt |
Closest papers by meaning
- Decentralized Cooperative Stochastic Bandits (NeurIPS 2019 · similarity 0.93)
- Decentralized Multi-Agent Linear Bandits with Safety Constraints (AAAI 2021 · similarity 0.92)
- Distributed Multi-Agent Bandits Over Erdős-Rényi Random Networks (NeurIPS 2025 · similarity 0.89)
- Individual Regret in Cooperative Stochastic Multi-Armed Bandits (NeurIPS 2025 · similarity 0.88)
- Adaptive Sample Sharing for Multi Agent Linear Bandits (ICML 2025 · similarity 0.87)
- Heavy-Tailed Linear Bandits: Huber Regression with One-Pass Update (ICML 2025 · similarity 0.87)
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.