AI Paper Atlas

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

Decentralized Gossip-Based Stochastic Bilevel Optimization over Communication Networks

Shuoguang Yang, Xuezhou Zhang, Mengdi Wang

NeurIPS 2022 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Decentralized actor-critic MARL · 4 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
Estimate the inverse averaged inner Hessian using a truncated matrix-product approximation and gossip-estimated HessiansGossip-based DSBO · Decentralized stochastic bilevel optimizationouter-gradient estimationImproved
Increase the number of agents from K=5 to K=10 or K=20Gossip-based DSBO · Australia handwriting datasetconvergence speed: K=5,10,20Improved
Replace gossip-based DSBO with the decentralized double-loop baseline DBSAAustralia handwriting dataset, K=5 · Australia handwriting datasetvalidation lossHurt
Replace gossip-based DSBO with the double-loop baseline DSGDMulti-agent MDP policy evaluation, K=5 · Multi-agent MDPmean square errorHurt
Increase the number of agents from K=5 to K=10 or K=20Gossip-based DSBO · Multi-agent MDP policy evaluationsamples to reach an ε-optimal solution: K = 5,10,20; 10^{-6}No 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