mlsanityData to 7 Oct 2026

Decentralized Safe Multi-agent Stochastic Optimal Control using Deep FBSDEs and ADMM

arXiv 2202.10658 ↗First posted 22 Feb 2022cs.MA cs.LG cs.ROcited by 3

Not on the map. Why?

Abstract (arXiv)

In this work, we propose a novel safe and scalable decentralized solution for multi-agent control in the presence of stochastic disturbances. Safety is mathematically encoded using stochastic control barrier functions and safe controls are computed by solving quadratic programs. Decentralization is achieved by augmenting to each agent's optimization variables, copy variables, for its neighbors. This allows us to decouple the centralized multi-agent optimization problem. However, to ensure safety, neighboring agents must agree on "what is safe for both of us" and this creates a need for consensus. To enable safe consensus solutions, we incorporate an ADMM-based approach. Specifically, we propose a Merged CADMM-OSQP implicit neural network layer, that solves a mini-batch of both, local quadratic programs as well as the overall consensus problem, as a single optimization problem. This layer is embedded within a Deep FBSDEs network architecture at every time step, to facilitate end-to-end differentiable, safe and decentralized stochastic optimal control. The efficacy of the proposed approach is demonstrated on several challenging multi-robot tasks in simulation. By imposing requirements on safety specified by collision avoidance constraints, the safe operation of all agents is ensured during the entire training process. We also demonstrate superior scalability in terms of computational and memory savings as compared to a centralized approach.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 30 of its 48 references that are in the map. First posted on arXiv 22 Feb 2022.

Builds on

30 of 48 references.

References · 30

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2018Neural Ordinary Differential Equationscited by 3,733
  4. 2015Continuous control with deep reinforcement learningcited by 3,279
  5. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  6. 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 723
  7. 2019Deep Equilibrium Modelscited by 603
  8. 2017OptNet: Differentiable Optimization as a Layer in Neural Networkscited by 588
  9. 2017Solving high-dimensional partial differential equations using deep learningcited by 549
  10. 2019Differentiable Convex Optimization Layerscited by 458
  11. 2019Control Barrier Functions: Theory and Applicationscited by 332
  12. 2020Scalable Gradients for Stochastic Differential Equationscited by 264
18 more
  1. 2016Control Barrier Function Based Quadratic Programs for Safety Critical Systemscited by 261
  2. 2019End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Taskscited by 256
  3. 2018Differentiable MPC for End-to-end Planning and Controlcited by 178
  4. 2017OSQP: An Operator Splitting Solver for Quadratic Programscited by 156
  5. 2017Safe Learning of Quadrotor Dynamics Using Barrier Certificatescited by 32
  6. 2019The Differentiable Cross-Entropy Methodcited by 26
  7. 2020Safe Optimal Control Using Stochastic Barrier Functions and Deep Forward-Backward SDEscited by 22
  8. 2019A Barrier Function Approach to Finite-Time Stochastic System Verification and Controlcited by 14
  9. 2020Control Barrier Functions for Stochastic Systemscited by 14
  10. 2019Learning Deep Stochastic Optimal Control Policies using Forward-Backward SDEscited by 13
  11. 2015Learning Optimal Control via Forward and Backward Stochastic Differential Equationscited by 11
  12. 2021A Survey of Distributed Optimization Methods for Multi-Robot Systemscited by 7
  13. 2019Deep Forward-Backward SDEs for Min-max Controlcited by 6
  14. 2020Large-Scale Multi-Agent Deep FBSDEscited by 5
  15. 2020Fast and Stable Nonconvex Constrained Distributed Optimization: The ELLADA Algorithmcited by 3
  16. 2020NOVAS: Non-convex Optimization via Adaptive Stochastic Search for End-to-End Learning and Controlcited by 2
  17. 2020High-Relative Degree Stochastic Control Lyapunov and Barrier Functionscited by 1
  18. 2021Alternating Direction Method of Multipliers-Based Parallel Optimization for Multi-Agent Collision-Free Model Predictive Controlcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025Discrete GCBF Proximal Policy Optimization for Multi-agent Safe Optimal Controlcited by 7
  2. 2025Solving Multi-Agent Safe Optimal Control with Distributed Epigraph Form MARLcited by 4
  3. 2026Safe and Generalizable Hierarchical Multi-Agent RL via Constraint Manifold Controlcited by 0