AI Paper Atlas

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

Self-Organized Group for Cooperative Multi-agent Reinforcement Learning

Jianzhun Shao, Zhiqiang Lou, Hongchang Zhang, Yuhang Jiang, Shuncheng He, Xiangyang Ji

NeurIPS 2022 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Cooperative MARL algorithms · 6 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 L_FP + L_CEB message summarizer losses together (ablation)SOG · Predator-Prey complicated scenariosaverage return: 7.2 -> 9.98Improved
add entropy regularizer to message loss (ablation)SOG · Predator-Prey complicated scenariosaverage return: 9.98 -> 7.31Hurt
add entropy regularizer to reduce variance (ablation)SOG · Predator-Preyreturn std: 1.15 -> 0.08Improved
number of groups 1 to 2 (ablation)SOG · Predator-Preytest return: 7.43 -> 9.90Improved
number of groups 2 to 4 (ablation)SOG · Predator-Preytest return: 9.90 -> 7.37Hurt
message dimension 10 to 3 (ablation)SOG · Predator-Preytest return: 10.77 -> 9.90No clear effect
message dimension 3 to 1 (ablation)SOG · Predator-Preytest return: 9.90 -> 6.30Hurt
communication interval T 4 to 2 (ablation)SOG · Predator-Preytest return: 9.90 -> 10Improved
communication interval T 4 to 10 (ablation)SOG · Predator-Preytest return: 9.90 -> 7.5Hurt
SOG vs EMP on complicated evaluation scenariosSOG · Predator-Preyaverage return: 9.37 -> 9.98Improved
PG-based conductor election instead of random (ablation)SOG · StarCraft 3-8sztest winning rateImproved
DPP/PG conductor election vs random on team-size changes (ablation)SOG · Resource Collectionaverage episode returnNo 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