AI Paper Atlas

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

SARL: Structure-Aligned Reinforcement Learning for Bridging the Perception-Action Gap in Airspace

Binhao Gu, jinjun cai, Weihuang Zheng, Jiaxing Li, Youyong Kong, Hui Ding

ICML 2026 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Cooperative MARL algorithms

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 Kinematic Safety Shield (ablation)SARL · BlueSky Case1success rate: 93.24 -> 99.28Improved
add Kinematic Safety Shield (ablation)SARL · BlueSky Case1collision rate: 4.76 -> 0.04Improved
add Kinematic Safety Shield (ablation)SARL · BlueSky Case1average operational cost: 123.83 -> 157.54Hurt
add PERG graph attention instead of fixed-size neighbor concatenation (ablation)baseline policy · Sparse/Medium/Dense trafficsuccess rateImproved
add SC-MoE action head (ablation)SARL without KSS · test set action distributionaction activation sparsityImproved
increase fixed neighbor count k in concatenation baseline (ablation)baseline policy · Sparse/Medium/Dense trafficsuccess rateMixed

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