# Non-Parametric Neuro-Adaptive Coordination of Multi-Agent Systems

arXiv: https://arxiv.org/abs/2110.05125 · HTML: https://mlsanity.com/paper/2110.05125/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 41 references that are in the map.
- First posted on arXiv 11 Oct 2021.

## Builds on (most cited first, 10 of 10)

- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms](https://mlsanity.com/paper/1911.10635/) (2019)
- [A Survey and Critique of Multiagent Deep Reinforcement Learning](https://mlsanity.com/paper/1810.05587/) (2018)
- [Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability](https://mlsanity.com/paper/1703.06182/) (2017)
- [Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1702.08887/) (2017)
- [Multi-Agent Reinforcement Learning via Double Averaging Primal-Dual Optimization](https://mlsanity.com/paper/1806.00877/) (2018)
- [Lessons from AlphaZero for Optimal, Model Predictive, and Adaptive Control](https://mlsanity.com/paper/2108.10315/) (2021)
- [Distributed Learning of Average Belief Over Networks Using Sequential Observations](https://mlsanity.com/paper/1811.07799/) (2018)
- [Robust Distributed Control Protocols for Large Vehicular Platoons with Prescribed Transient and Steady State Performance](https://mlsanity.com/paper/1701.06438/) (2017)
- [Robust Formation Control in SE(3) for Tree-Graph Structures with Prescribed Transient and Steady State Performance](https://mlsanity.com/paper/1803.07513/) (2018)

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

- [DATT: Deep Adaptive Trajectory Tracking for Quadrotor Control](https://mlsanity.com/paper/2310.09053/) (2023)

## Abstract (arXiv)

We develop a learning-based algorithm for the distributed formation control of networked multi-agent systems governed by unknown, nonlinear dynamics. Most existing algorithms either assume certain parametric forms for the unknown dynamic terms or resort to unnecessarily large control inputs in order to provide theoretical guarantees. The proposed algorithm avoids these drawbacks by integrating neural network-based learning with adaptive control in a two-step procedure. In the first step of the algorithm, each agent learns a controller, represented as a neural network, using training data that correspond to a collection of formation tasks and agent parameters. These parameters and tasks are derived by varying the nominal agent parameters and the formation specifications of the task in hand, respectively. In the second step of the algorithm, each agent incorporates the trained neural network into an online and adaptive control policy in such a way that the behavior of the multi-agent closed-loop system satisfies a user-defined formation task. Both the learning phase and the adaptive control policy are distributed, in the sense that each agent computes its own actions using only local information from its neighboring agents. The proposed algorithm does not use any a priori information on the agents' unknown dynamic terms or any approximation schemes. We provide formal theoretical guarantees on the achievement of the formation task.