Research map / Bandits and online learning / Multi-armed bandits
Fair Algorithms with Probing for Multi-Agent Multi-Armed Bandits
Tianyi Xu, Jiaxin Liu, Nicholas Mattei, Zizhan Zheng
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 |
|---|---|---|---|
| add greedy probing with fair (NSW) assignment (OFMUP) | Random probing with random assignment · Synthetic Bernoulli M=12, A=8 | cumulative regret at T=3000: 85% lower regret | Improved |
| replace random assignment with NSW-optimal assignment after greedy probing (ablation) | Greedy P+A · Synthetic Bernoulli M=12, A=8 | cumulative regret at T=3000: 60% lower regret | Improved |
| replace random assignment with NSW-optimal assignment after greedy probing (ablation) | Greedy P+A · Synthetic Bernoulli M=20, A=10 | cumulative regret at T=3000: 80% lower regret | Improved |
| add probing to fair bandit algorithm (ablation) | Non-Probing fair MAB (Jones et al.) · Synthetic discrete rewards | cumulative regret at T=3000: 65% lower regret | Improved |
| increase problem scale (more agents and arms) | OFMUP · Synthetic scalability | regret advantage over baselines | Improved |
| piecewise-linear upper bound f_upper in place of log g(S) | offline probing objective · Synthetic offline | approximation gap: difference 0.03 | No clear effect |
| small-scale setting for Random P+A | Random P+A · Synthetic Bernoulli M=12, A=8 | cumulative regret | Hurt |
Closest papers by meaning
- Nash Social Welfare for Multi Armed Bandits: Trajectory-wise Expected and High Probability Regret (NeurIPS 2026 · similarity 0.90)
- Honor Among Bandits: No-Regret Learning for Online Fair Division (NeurIPS 2024 · similarity 0.88)
- No-Regret Learning for Fair Multi-Agent Social Welfare Optimization (NeurIPS 2024 · similarity 0.88)
- Optimal Algorithm for Max-Min Fair Bandit (ICML 2025 · similarity 0.87)
- Heterogeneous Multi-Agent Bandits with Parsimonious Hints (AAAI 2025 · similarity 0.87)
- Robust Performance Incentivizing Algorithms for Multi-Armed Bandits with Strategic Agents (AAAI 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.
