AI Paper Atlas

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

Learning Disentangled Multi-Agent World Model for Decentralized Control

Di Xue, Jing Jiang, Shaowei Zhang, Wenhao Guo, Lei Yuan, Zongzhang Zhang, Yang Yu

ICML 2026 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Coordination graphs

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 transformer-based centralized critic (vs MLP critic, DMAWM-TC) (ablation)DMAWM · SMACv2 protoss 5 vs 5win rateImproved
add transformer-based interaction predictor (vs per-agent MLP, DMAWM-IP) (ablation)DMAWM · SMACv2 protoss 5 vs 5win rateImproved
add off-policy critic loss grounded on real trajectories (vs beta_off = 0, DMAWM-OC) (ablation)DMAWM · SMACv2 protoss 5 vs 5win rateImproved
lengthen the imagination horizon (4 to 20) (ablation)DMAWM · SMACv2 (3 maps)win rateNo clear effect
align joint prior with factorized posterior to disentangle agent latents (vs communication-based MAMBA)DMAWM · SMACv2 protoss 5 vs 5unobservable-teammate action prediction accuracy: 85.0% -> 42.3% (lower means less leakage)Improved
use disentangled latent world model instead of MAMBADMAWM · SMAC corridorwin rate: 18.6 -> 71.5Improved
use disentangled latent world model instead of MAPPO on a trivial mapDMAWM · SMAC 2s vs 1scwin rate: 100.0 -> 98.3No clear effect
use DMAWM instead of MAPPO trained with 10x more environment stepsDMAWM · SMACv2win rateImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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