AI Paper Atlas

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

Safe Multi-agent Reinforcement Learning with Natural Language Constraints

Ziyan Wang, Meng Fang, Tristan Tomilin, Fei Fang, Yali Du

AAAI 2026 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Cooperative MARL algorithms · 17 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
add SMALL learned language costs to HAPPO/MAPPOHAPPO · LaMaSafe-Goal (Ant, easy)cost: 22.4 -> 5.8Improved
add SMALL learned language costs to HAPPO/MAPPOHAPPO · LaMaSafe-Goal (Ant, easy)reward: 12.5 -> 11.6No clear effect
add SMALL costs to MAPPO/HAPPOLaMaSafe-Highway · LaMaSafe-Highwayreward: about 10-15% lower in some casesHurt
use real constraint embeddings instead of random vectors (ablation)SMALL-HAPPO · LaMaSafe-Goal (Ant, easy)cost: 34.5 -> 5.8Improved
add triplet fine-tuning of the encoder (ablation)SMALL-HAPPO · LaMaSafe-Goal (Ant, easy)reward: 6.3 -> 11.6Improved
add the validation LLM (ablation)SMALL-HAPPO · LaMaSafe-Goal (Ant, easy)cost: 10.8 -> 5.8Improved
add the rule-based descriptor (ablation)SMALL-HAPPO · LaMaSafe-Goal (Ant, easy)reward: 7.9 -> 11.6Improved
add the binary violation flag to the cost (ablation)SMALL-HAPPO · LaMaSafe-Goal (Ant, easy)reward: 5.1 -> 11.6Improved

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