AI Paper Atlas

Research map / Multi-agent systems and games / Cooperative multi-agent RL

Learning Fairness in Multi-Agent Systems

Jiechuan Jiang, Zongqing Lu

NeurIPS 2019 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Decentralized actor-critic MARL · 11 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
Use FEN's fair-efficient reward and hierarchical controller with specialized sub-policies instead of Independent agentsMulti-agent system · Job schedulingCV: 1.57 -> 0.17Improved
Use FEN instead of Independent agentsMulti-agent system · Job schedulingresource utilization: 96% -> 90%Hurt
Use FEN instead of Min+αAvgMulti-agent system · Job schedulingCV: 0.39 -> 0.17Improved
Remove the hierarchy (ablation)FEN · Job schedulingresource utilization: 90% -> 57%Hurt
Add the hierarchy (ablation)FEN · Job schedulingCV: 0.22 -> 0.17Improved
Add the hierarchy (ablation)FEN · The Matthew effectepisodes to converge: 6000 -> 300Improved
Use FEN instead of Independent agentsMulti-agent system · The Matthew effectsocial welfare: 791 -> 830Improved
Use FEN instead of Independent agentsMulti-agent system · The Matthew effectCV: 0.86 -> 0.06Improved
Estimate average utility with local gossip consensus (ablation)FEN · The Matthew effectCV: 0.06 -> 0.07No clear effect
Replace learned fairness sub-policies with a random sub-policy (ablation)FEN · The Matthew effectCV: 0.06 -> 0.08Hurt
Use FEN instead of Min+αAvgMulti-agent system · Manufacturing plantno. products: 23 -> 48Improved
Use FEN instead of Min+αAvgMulti-agent system · Manufacturing plantresource utilization: 34% -> 82%Improved

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