AI Paper Atlas

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

Learning Distributed and Fair Policies for Network Load Balancing as Markov Potential Game

Zhiyuan YAO, Zihan Ding

NeurIPS 2022 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Cooperative MARL algorithms · 2 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 log term to VBF reward (ablation)Distr-LB · Real-world moderate, Period III Wikiaverage QoS (s): 0.159 -> 0.108Improved
add log term to VBF reward (ablation)Distr-LB · Real-world moderate, Period IV Staticaverage QoS (s): 0.032 -> 0.006Improved
add log term to VBF reward (ablation)Distr-LB · Simulator 50%-CPU+50%-IOaverage QoS (s): 10.335 -> 8.797Improved
add log term to VBF reward (ablation)Distr-LB · Simulator 100%-CPUaverage QoS (s): 1.643 -> 2.004Hurt
add log term to VBF reward (ablation)Distr-LB · Simulator 75%-CPU+25%-IOaverage QoS (s): 1.695 -> 1.873Hurt
add log term to VBF reward (ablation)Distr-LB · Real-world large, Period I Wikiaverage QoS (s): 0.228 -> 0.161Improved
use distributed Distr-LB instead of centralised Centr-LBDistr-LB · Real-world moderate, Period III Wikiaverage QoS (s): 0.759 -> 0.108Improved
use Distr-LB instead of SEDDistr-LB · Real-world moderate, Period III Staticaverage QoS (s): 0.051 -> 0.004Improved
use Distr-LB instead of RLB-SAC (G)Distr-LB · Real-world moderate, Period IV Wikiaverage QoS (s): 0.155 -> 0.104Improved
use Distr-LB (VBF) instead of QMix-LB (PBF)Distr-LB · Simulator 100%-CPUaverage QoS (s): 2.200 -> 1.643Improved
use Distr-LB (VBF+logVBF) instead of QMix-LB (VBF)Distr-LB · Real-world moderate, Period IV Wikiaverage QoS (s): 0.286 -> 0.104Improved
use Distr-LB instead of QMix-LB (VBF)Distr-LB · Real-world moderate, Period III Wikiaverage QoS (s): 0.141 -> 0.159No clear effect

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