AI Paper Atlas

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

AAAI 2026 · Bandits and online learning › Multi-armed bandits · approach: Multi-agent bandits · 1 citations (OpenAlex)

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 changedWhereMeasuredEffect
add greedy probing with fair (NSW) assignment (OFMUP)Random probing with random assignment · Synthetic Bernoulli M=12, A=8cumulative regret at T=3000: 85% lower regretImproved
replace random assignment with NSW-optimal assignment after greedy probing (ablation)Greedy P+A · Synthetic Bernoulli M=12, A=8cumulative regret at T=3000: 60% lower regretImproved
replace random assignment with NSW-optimal assignment after greedy probing (ablation)Greedy P+A · Synthetic Bernoulli M=20, A=10cumulative regret at T=3000: 80% lower regretImproved
add probing to fair bandit algorithm (ablation)Non-Probing fair MAB (Jones et al.) · Synthetic discrete rewardscumulative regret at T=3000: 65% lower regretImproved
increase problem scale (more agents and arms)OFMUP · Synthetic scalabilityregret advantage over baselinesImproved
piecewise-linear upper bound f_upper in place of log g(S)offline probing objective · Synthetic offlineapproximation gap: difference 0.03No clear effect
small-scale setting for Random P+ARandom P+A · Synthetic Bernoulli M=12, A=8cumulative regretHurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy