Research map / Bandits and online learning / Multi-armed bandits
An Efficient Algorithm for Fair Multi-Agent Multi-Armed Bandit with Low Regret
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 Fair multi-agent UCB instead of Prior UCB | MA-MAB (N=4, K=2) · MA-MAB (N=4, K=2), t=2·10^5 and t=5·10^5 | average cumulative regret: 1226 -> 1222; 1832 -> 1806 | Helped |
| Use Fair multi-agent UCB instead of Prior UCB | MA-MAB (N=20, K=4) · MA-MAB (N=20, K=4), t=2·10^5 and t=5·10^5 | average cumulative regret: 10801 -> 8313; 21655 -> 15322 | Helped |
| Use Fair multi-agent UCB instead of Prior UCB | MA-MAB (N=80, K=8) · MA-MAB (N=80, K=8), t=2·10^5 and t=5·10^5 | average cumulative regret: 5230 -> 4521; 12874 -> 9966 | Helped |
| Use Fair multi-agent UCB instead of Prior UCB at early iterations | MA-MAB with small N and K · MA-MAB, small sizes and t under 10,000 | cumulative regret | Mixed |
| Use the confidence-bound UCB variant with α_t = √(12NK log(NKt)) instead of α_t = N (ablation) | Prior UCB · MA-MAB experiments | cumulative regret | Hurt |
Closest papers by meaning
- No-Regret Learning for Fair Multi-Agent Social Welfare Optimization (NeurIPS 2024 · similarity 0.92)
- Honor Among Bandits: No-Regret Learning for Online Fair Division (NeurIPS 2024 · similarity 0.91)
- Improved Regret Bounds for Online Fair Division with Bandit Learning (AAAI 2025 · similarity 0.90)
- Nash Social Welfare for Multi Armed Bandits: Trajectory-wise Expected and High Probability Regret (NeurIPS 2026 · similarity 0.89)
- Federated Combinatorial Multi-Agent Multi-Armed Bandits (ICML 2024 · similarity 0.89)
- Distributed Multi-Agent Bandits Over Erdős-Rényi Random Networks (NeurIPS 2025 · 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.