Scalable Safe Multi-Agent Reinforcement Learning for Multi-Agent System

2025-01-23 · Haikuo Du, Fandi Gou, Yunze Cai

Safety and scalability are two critical challenges faced by practical Multi-Agent Systems (MAS). However, existing Multi-Agent Reinforcement Learning (MARL) algorithms that rely solely on reward shaping are ineffective in ensuring safety, and their scalability is rather limited due to the fixed-size network output. To address these issues, we propose a novel framework, Scalable Safe MARL (SS-MARL), to enhance the safety and scalability of MARL methods. Leveraging the inherent graph structure of MAS, we design a multi-layer message passing network to aggregate local observations and communications of varying sizes. Furthermore, we develop a constrained joint policy optimization method in the setting of local observation to improve safety. Simulation experiments demonstrate that SS-MARL achieves a better trade-off between optimality and safety compared to baselines, and its scalability significantly outperforms the latest methods in scenarios with a large number of agents.

📄 PDF Abstract BibTeX arXiv:2501.13727

Code (1)

qeneb/ss-marl 공식 구현 pytorch

Tasks

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning

Methods 이 논문이 사용한 방법론

MAS This optimizer mix ADAM and SGD creating the MAS optimizer.

Safe Multi-Agent Reinforcement Learning via Shielding

2021-01-27 · Ingy Elsayed-Aly, Suda Bharadwaj, Christopher Amato, Rüdiger Ehlers 외

Multi-agent reinforcement learning (MARL) has been increasingly used in a wide range of safety-critical applications, which require guaranteed safety (e.g., no unsafe states are ever visited) during the learning process.…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

DeepSafeMPC: Deep Learning-Based Model Predictive Control for Safe Multi-Agent Reinforcement Learning

2024-03-11 · Xuefeng Wang, Henglin Pu, Hyung Jun Kim, Husheng Li

Safe Multi-agent reinforcement learning (safe MARL) has increasingly gained attention in recent years, emphasizing the need for agents to not only optimize the global return but also adhere to safety requirements through…

Model Predictive Control MuJoCo Multi-agent Reinforcement Learning reinforcement-learning+1

Approximating Shapley Explanations in Reinforcement Learning

2025-11-08 · Daniel Beechey, Özgür Şimşek arxiv

Reinforcement learning has achieved remarkable success in complex decision-making environments, yet its lack of transparency limits its deployment in practice, especially in safety-critical settings. Shapley values from …

Reinforcement Learning

Probabilistic Shielding for Safe Reinforcement Learning

2025-03-09 · Edwin Hamel-De le Court, Francesco Belardinelli, Alexander W. Goodall

In real-life scenarios, a Reinforcement Learning (RL) agent aiming to maximise their reward, must often also behave in a safe manner, including at training time. Thus, much attention in recent years has been given to Saf…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Safe Reinforcement Learning

Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models

2025-06-09 · Mickel Liu, Liwei Jiang, Yancheng Liang, Simon Shaolei Du 외

Conventional language model (LM) safety alignment relies on a reactive, disjoint procedure: attackers exploit a static model, followed by defensive fine-tuning to patch exposed vulnerabilities. This sequential approach c…

Multi-agent Reinforcement Learning Safety Alignment