atlas

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

Communication-Efficient Topologies for Decentralized Learning with $O(1)$ Consensus Rate

NeurIPS 2022 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Decentralized actor-critic MARL · 2 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use D-EquiStatic instead of Static Exp.DSGD with ResNet-20 · CIFAR-10test accuracy: 91.5% -> 92%Helped
Use U-EquiStatic instead of Static Exp.DSGD with ResNet-20 · CIFAR-10test accuracy: 91.5% -> 91.7%Helped
Use bidirectional U-EquiStatic instead of directed D-EquiStaticDSGD · Distributed least-square problemsconvergence speedHelped
Use OD/OU-EquiDyn instead of other compared topologiesDSGD · Decentralized stochastic optimizationtransient iteration complexityHelped
Use OD/OU-EquiDyn instead of other compared topologiesDSGT · Decentralized stochastic optimizationtransient iteration complexityHelped
Use OD-EquiDyn instead of other compared degree-1 topologiesGossip averaging · n=4900consensus speedHelped

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