Safe MARL

MARL: Multi-Agent Reinforcement Learning

Latest papers

9 papers2 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

CARGO: Causal Attribution and Responsibility-Guided Preventive Safe Multi-Agent Reinforcement Learning for Cooperative Driving
Nov 6, 2026Jingjia Teng, Yang Li, Wenjie HuangSafe MARL RL for Autonomous Driving
State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle, College of Mechanical and Vehicle Engineering, Hunan University, Changsha 410082, China.
Safeguarding Multi-Agent Reinforcement Learning for Connected and Automated Vehicles with Recursively Feasible Control Barrier Functions
Nov 3, 2026Jianye Xu, Yousef Sayed, Bassam AlrifaeeSafe MARL Control Barrier Functions
Department of Computer Science, RWTH Aachen University, Germany · Department of Aerospace Engineering, University of the Bundeswehr Munich, Germany
Vulnerability Analysis for Safe Multi-Agent Reinforcement Learning
Oct 19, 2026Taozheng Zhu, Shixiong Jiang, Fanxin KongSafe MARL Adversarial Attacks
University of Notre Dame Notre Dame, Indiana, USA
SafeDiSTL: Decomposing Joint Constraints for Safe Multi-Agent Reinforcement Learning
Oct 9, 2026Hongrui Zheng, Aditya Singh, Rahul MangharamSafe MARL Constrained MARL
University of Pennsylvania, Philadelphia, USA
Fully Decentralized and Safety-Aware Multi-Agent Reinforcement Learning for Control on Networks
Sep 28, 2026Theodore Rogalski, Shirantha WelikalaSafe MARL Multi-Agent Control
Electrical & Computer Engineering Department Stevens Institute of Technology Hoboken, USA
Decentralized Safe Multi-Agent Reinforcement Learning via Predictive Shielding
Sep 7, 2026Yacine El Yamani, Hanna Krasowski, Elena VanneauxSafe MARL Multi-Robot Coordination
ENSTA, IP Paris, Palaiseau, France · UC Berkeley, USA
Safe and Generalizable Hierarchical Multi-Agent RL via Constraint Manifold Control
Jun 22, 2026Zihao Guo, Jianing Zhao, Ling Li +3Multi-Agent Reinforcement Learning Safe MARL
1King’s College London · University of California, Berkeley · 3The Alan Turing Institute
Safe Equilibrium Policy Optimization for Strategic Agent Policies
May 29, 2026Karthika Arumugam, Kiran Kumar Manku, Amit DhandaMulti-Agent Reinforcement Learning Multi-Agent System Optimization
†Amazon, USA
Safe Multi-Agent Deep Reinforcement Learning for Privacy-Aware Edge-Device Collaborative DNN Inference
Feb 23, 2026Hong Wang, Xuwei Fan, Zhipeng Cheng +4Safe MARL Hierarchical MARL
School of Future Science and Engineering, Soochow University, Suzhou 215006, China · College of Computer and Information Sciences, Fujian Agriculture and Forestry University, Fuzhou 350002, China · School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, China +2

Nov 6, 2026J/K move · Enter open · S save

CARGO: Causal Attribution and Responsibility-Guided Preventive Safe Multi-Agent Reinforcement Learning for Cooperative Driving

Jingjia Teng, Yang Li, Wenjie Huang

State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle, College of Mechanical and Vehicle Engineering, Hunan University, Changsha 410082, China.

Safe MARL RL for Autonomous Driving Cooperative MARL Multi-Agent Reinforcement Learning Constrained MARL Causal RL

Open paper AskPDF arXiv

This study presents Causal Attribution and Responsibility-Guided Optimization (CARGO), a multi-agent reinforcement learning framework for cooperative on-ramp merging in mixed traffic. A shared latent-context posterior and an action-conditioned response model estimate directed behavioral influence, with posterior uncertainty propagated into interaction-edge selection. Complementary attribution mechanisms couple signed influence with marginal team utility for cooperative reward shaping and assign responsibility from positive excess tail risk relative to a safe reference policy. Conditional diffusion generates future responses for action-dependent risk estimation. Responsibility-guided preventive optimization calibrates agent-specific risk-reduction requirements to local capacity within a policy trust region, using reserved safety margins, adaptive requirement scaling, and joint feasibility verification. Theoretical analysis establishes risk monotonicity and sufficient local conditions for non-decreasing environmental return under explicit assumptions. Experiments in highway-env across three traffic densities, together with controlled graph-recovery and attribution studies, support the effectiveness of the framework. Under high-density traffic, CARGO increases the success rate by 66.04% and reduces the crash rate by 56.23% relative to the best evaluated baseline for each metric.