mlsanityData to 7 Oct 2026

Individual Control Barrier Functions-Guided Diffusion Model for Safe Offline Multi-Agent Reinforcement Learning

arXiv 2606.12640 ↗First posted 10 Jun 2026cs.LG cs.RO cs.SYcited by 0

On the map: Diffusion models → Diffusion and flow policies for robotics

also in 1 more
Abstract (arXiv)

Offline reinforcement learning allows control policies to be learned directly from data without online interaction, making it suitable for safety-critical tasks. Recent studies have applied diffusion models to offline reinforcement learning to leverage their strong capacity for modeling complex data distributions. However, existing approaches primarily focus on single-agent settings, leaving the safety challenges in multi-agent environments largely unexplored. In this work, we propose a safe offline multi-agent reinforcement learning algorithm that embeds neural individual control barrier functions into the diffusion model to enhance safety during trajectory generation, with control policies recovered through inverse dynamics. We evaluate our algorithm across diverse benchmarks, demonstrating substantial safety improvements while maintaining competitive rewards.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models. Builds on 17 of its 26 references that are in the map. First posted on arXiv 10 Jun 2026.

Builds on

17 of 26 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023SafeDiffuser: Safe Planning with Diffusion Probabilistic Models31 May
  2. 2023MADiff: Offline Multi-agent Learning with Diffusion Models27 May
  3. 2022Is Conditional Generative Modeling all you need for Decision-Making?28 Nov

Other references · 14

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2017Constrained Policy Optimizationcited by 928
  3. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 903
  4. 2021A Minimalist Approach to Offline Reinforcement Learningcited by 882
  5. 2021Learning Safe Multi-Agent Control with Decentralized Neural Barrier Certificatescited by 71
  6. 2022Safe Reinforcement Learning by Imagining the Near Futurecited by 67
  7. 2024Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Modelcited by 62
  8. 2021Safe Multi-Agent Reinforcement Learning via Shieldingcited by 60
  9. 2021Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectificationcited by 59
  10. 2022Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environmentscited by 54
  11. 2019Safe Reinforcement Learning on Autonomous Vehiclescited by 48
  12. 2019Reducing Overestimation Bias in Multi-Agent Domains Using Double Centralized Criticscited by 46
2 more
  1. 2023Learning Adaptive Safety for Multi-Agent Systemscited by 3
  2. 2020Lyapunov-Based Reinforcement Learning for Decentralized Multi-Agent Controlcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Diffusion Models for Offline Multi-agent Reinforcement Learning with Safety Constraints
  2. 2023Guided Online Distillation: Promoting Safe Reinforcement Learning by Offline Demonstration
  3. 2025Don't Trade Off Safety: Diffusion Regularization for Constrained Offline RL
  4. 2026Decoupled Guidance Diffusion for Adaptive Offline Safe Reinforcement Learning
  5. 2026Discriminative Barrier Functions for Safe Adversarial Imitation Learning from Observation
  6. 2026Reachability-Aware Diffusion Policy Optimization
  7. 2026CDCP: Conditional Diffusion Model with Contextual Prompts for Multi-task Offline Safe Reinforcement Learning
  8. 2026How Does the Lagrangian Guide Safe Reinforcement Learning through Diffusion Models?