# Towards safe control parameter tuning in distributed multi-agent systems

arXiv: https://arxiv.org/abs/2508.13608 · HTML: https://mlsanity.com/paper/2508.13608/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 41 references that are in the map.
- First posted on arXiv 19 Aug 2025.

## Builds on (most cited first, 25 of 25)

- [A Tutorial on Bayesian Optimization](https://mlsanity.com/paper/1807.02811/) (2018)
- [Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning](https://mlsanity.com/paper/2108.06266/) (2021)
- [On Kernelized Multi-armed Bandits](https://mlsanity.com/paper/1704.00445/) (2017)
- [Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents](https://mlsanity.com/paper/1802.08757/) (2018)
- [Bayesian Optimization with Safety Constraints: Safe and Automatic Parameter Tuning in Robotics](https://mlsanity.com/paper/1602.04450/) (2016)
- [Stagewise Safe Bayesian Optimization with Gaussian Processes](https://mlsanity.com/paper/1806.07555/) (2018)
- [Recent Advances in Bayesian Optimization](https://mlsanity.com/paper/2206.03301/) (2022)
- [Safe Exploration for Interactive Machine Learning](https://mlsanity.com/paper/1910.13726/) (2019)
- [Time-Varying Gaussian Process Bandit Optimization](https://mlsanity.com/paper/1601.06650/) (2016)
- [Practical and Rigorous Uncertainty Bounds for Gaussian Process Regression](https://mlsanity.com/paper/2105.02796/) (2021)
- [Monte Carlo Tree Search based Variable Selection for High Dimensional Bayesian Optimization](https://mlsanity.com/paper/2210.01628/) (2022)
- [Automatic LQR Tuning Based on Gaussian Process Global Optimization](https://mlsanity.com/paper/1605.01950/) (2016)
- [High Dimensional Bayesian Optimization via Supervised Dimension Reduction](https://mlsanity.com/paper/1907.08953/) (2019)
- [On Controller Tuning with Time-Varying Bayesian Optimization](https://mlsanity.com/paper/2207.11120/) (2022)
- [Learning Safe Control for Multi-Robot Systems: Methods, Verification, and Open Challenges](https://mlsanity.com/paper/2311.13714/) (2023)
- [Automatic nonlinear MPC approximation with closed-loop guarantees](https://mlsanity.com/paper/2312.10199/) (2023)
- [Near-Optimal Multi-Agent Learning for Safe Coverage Control](https://mlsanity.com/paper/2210.06380/) (2022)
- [Safe exploration in reproducing kernel Hilbert spaces](https://mlsanity.com/paper/2503.10352/) (2025)
- [PACSBO: Probably approximately correct safe Bayesian optimization](https://mlsanity.com/paper/2409.01163/) (2024)
- [Gaussian Max-Value Entropy Search for Multi-Agent Bayesian Optimization](https://mlsanity.com/paper/2303.05694/) (2023)
- [Safe Bayesian Optimization for the Control of High-Dimensional Embodied Systems](https://mlsanity.com/paper/2412.20350/) (2024)
- [Cooperative look-ahead control for fuel-efficient and safe heavy-duty vehicle platooning](https://mlsanity.com/paper/1505.00447/) (2015)
- [Distributed Thompson sampling under constrained communication](https://mlsanity.com/paper/2410.15543/) (2024)
- [Mean-Field Bayesian Optimisation](https://mlsanity.com/paper/2502.12315/) (2025)
- [Cyber-physical Control of Road Freight Transport](https://mlsanity.com/paper/1507.03466/) (2015)

## Abstract (arXiv)

Many safety-critical real-world problems, such as autonomous driving and collaborative robots, are of a distributed multi-agent nature. To optimize the performance of these systems while ensuring safety, we can cast them as distributed optimization problems, where each agent aims to optimize their parameters to maximize a coupled reward function subject to coupled constraints. Prior work either studies a centralized setting, does not consider safety, or struggles with sample efficiency. Since we require sample efficiency and work with unknown and nonconvex rewards and constraints, we solve this optimization problem using safe Bayesian optimization with Gaussian process regression. Moreover, we consider nearest-neighbor communication between the agents. To capture the behavior of non-neighboring agents, we reformulate the static global optimization problem as a time-varying local optimization problem for each agent, essentially introducing time as a latent variable. To this end, we propose a custom spatio-temporal kernel to integrate prior knowledge. We show the successful deployment of our algorithm in simulations.