# Layered controller synthesis for dynamic multi-agent systems

arXiv: https://arxiv.org/abs/2307.06758 · HTML: https://mlsanity.com/paper/2307.06758/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 35 references that are in the map.
- First posted on arXiv 13 Jul 2023.

## Builds on (most cited first, 7 of 7)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [A Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06860/) (2021)
- [Unifying Count-Based Exploration and Intrinsic Motivation](https://mlsanity.com/paper/1606.01868/) (2016)
- [A Policy Search Method For Temporal Logic Specified Reinforcement Learning Tasks](https://mlsanity.com/paper/1709.09611/) (2017)
- [Scalable and Safe Multi-Agent Motion Planning with Nonlinear Dynamics and Bounded Disturbances](https://mlsanity.com/paper/2012.09052/) (2020)
- [What's decidable about parametric timed automata?](https://mlsanity.com/paper/1907.01721/) (2019)

## Built on by (most cited first, 1 of 1)

- [A Parametric Model for Near-Optimal Online Synthesis with Robust Reach-Avoid Guarantees](https://mlsanity.com/paper/2504.01006/) (2025)

## Abstract (arXiv)

In this paper we present a layered approach for multi-agent control problem, decomposed into three stages, each building upon the results of the previous one. First, a high-level plan for a coarse abstraction of the system is computed, relying on parametric timed automata augmented with stopwatches as they allow to efficiently model simplified dynamics of such systems. In the second stage, the high-level plan, based on SMT-formulation, mainly handles the combinatorial aspects of the problem, provides a more dynamically accurate solution. These stages are collectively referred to as the SWA-SMT solver. They are correct by construction but lack a crucial feature: they cannot be executed in real time. To overcome this, we use SWA-SMT solutions as the initial training dataset for our last stage, which aims at obtaining a neural network control policy. We use reinforcement learning to train the policy, and show that the initial dataset is crucial for the overall success of the method.