Diffusion Models For Offline Multi-agent Reinforcement Learning With Safety Constraints

Abstract

In recent advancements in Multi-agent Reinforcement Learning (MARL), its application has extended to various safety-critical scenarios. However, most methods focus on online learning, which presents substantial risks when deployed in real-world settings. Addressing this challenge, we introduce an innovative framework integrating diffusion models within the MARL paradigm. This approach notably enhances the safety of actions taken by multiple agents through risk mitigation while modeling coordinated action. Our framework is grounded in the Centralized Training with Decentralized Execution (CTDE) architecture, augmented by a Diffusion Model for prediction trajectory generation. Additionally, we incorporate a specialized algorithm to further ensure operational safety. We evaluate our model against baselines on the DSRL benchmark. Experiment results demonstrate that our model not only adheres to stringent safety constraints but also achieves superior performance compared to existing methodo

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhuang2024diffusion

Related papers

• Madiff: Offline Multi-agent Learning With Diffusion Models (2023)2.26
• Beyond Conservatism: Diffusion Policies In Offline Multi-agent Reinforcement Learning (2023)0.00
• Diffusion-based Episodes Augmentation For Offline Multi-agent Reinforcement Learning (2024)0.00
• Safe Multi-agent Reinforcement Learning With Convergence To Generalized Nash Equilibrium (2024)0.00
• How Does The Lagrangian Guide Safe Reinforcement Learning Through Diffusion Models? (2026)0.00
• Decoupled Guidance Diffusion For Adaptive Offline Safe Reinforcement Learning (2026)0.00
• Deepsafempc: Deep Learning-based Model Predictive Control For Safe Multi-agent Reinforcement Learning (2024)0.00
• One Risk To Rule Them All: A Risk-sensitive Perspective On Model-based Offline Reinforcement Learning (2022)3.58