AI Paper Atlas

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

TACTIC: Task-Aware Sparse Coordination Graphs for Multi-Task Multi-agent Reinforcement Learning

Kexing Peng, Pengyi Li, tinghuai ma, Jianye HAO

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 trajectory abstraction (VQ-VAE classes) (ablation)TACTIC · SMACv2 10zerg and 10terranwin rateImproved
add coverage loss (ablation)TACTIC · SMACv2 10zerg and 10terranwin rateImproved
use dynamic task-conditioned graph instead of random graph (ablation)TACTIC · SMACv2win rateImproved
add trajectory classification and graph modulation together (ablation)TACTIC · SMACv2win rateImproved
use dynamic graph instead of static graph (ablation)TACTIC · reSurComb3/4 (mirrored tasks)returnHurt
use dynamic graph instead of static graph (ablation)TACTIC · SurComb3/4returnImproved
add full semantic-to-structure coupling instead of only a dynamic graph on TRAMA backbone (ablation)TACTIC · SMACv2 SurComb3reward: 2.38 -> 2.80Improved
update graph every 5 steps instead of every step at inference (ablation)TACTIC · SMACv2 SurComb3reward: 2.80 -> 2.73Mixed
update graph every 10 steps instead of every step at inference (ablation)TACTIC · SMACv2 SurComb3reward: 2.80 -> 2.65Mixed
use static graph per episode instead of per-step adaptive (ablation)TACTIC · SMACv2 SurComb3reward: 2.80 -> 2.50Hurt
use TACTIC instead of Random policyTACTIC · SUMO intersectionarrival time (s): 18.60 -> 15.90Improved
use TACTIC instead of Random policyTACTIC · SUMO intersectionfuel (mg): 21813.26 -> 19008.64Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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