Research map / Bandits and online learning / Multi-armed bandits
Collaborative Multi-Agent Heterogeneous Multi-Armed 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 collaborative gossip recommendations instead of learning without communication | Modified GosInE · Multi-agent heterogeneous MAB, per-agent regret | expected cumulative regret | Helped |
| Give each agent knowledge of r-1 agents learning the same bandit and distribute recent unique recommendations | Partially context-aware algorithm versus modified GosInE · Multi-agent heterogeneous MAB, per-agent regret | expected cumulative regret: O\left(\frac{\frac{MK}{N}+M}{\Delta_m}\log T\right) -> O\left(\frac{\frac{MK}{N}+\frac{M}{r}}{\Delta_m}\log T\right) | Helped |
| Use collaborative gossip recommendations instead of no communication | Modified GosInE · Multi-agent heterogeneous MAB, simulated group regret | group cumulative regret | Helped |
| Add same-bandit peer awareness and divide recent unique recommendations among peers | Partially context-aware algorithm versus modified GosInE · Multi-agent heterogeneous MAB, simulated group regret | group cumulative regret | Helped |
| Distribute exploration of the M best-arm recommendations among r same-bandit agents | Partially context-aware algorithm · Multi-agent heterogeneous MAB, per-agent regret | expected cumulative regret: O\left(\frac{M}{\Delta_m} \log T\right) -> O\left(\frac{M}{r\Delta_m} \log T\right) | Helped |
Closest papers by meaning
- Communication-Efficient Collaborative Regret Minimization in Multi-Armed Bandits (AAAI 2024 · similarity 0.92)
- Distributed Multi-Agent Bandits Over Erdős-Rényi Random Networks (NeurIPS 2025 · similarity 0.91)
- Individual Regret in Cooperative Stochastic Multi-Armed Bandits (NeurIPS 2025 · similarity 0.89)
- Adaptive Sample Sharing for Multi Agent Linear Bandits (ICML 2025 · similarity 0.89)
- Heterogeneous Multi-Agent Bandits with Parsimonious Hints (AAAI 2025 · similarity 0.89)
- Federated Combinatorial Multi-Agent Multi-Armed Bandits (ICML 2024 · 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.