The networked nature of multi-robot systems presents challenges in the context of multi-agent reinforcement learning. Centralized control policies do not scale with increasing numbers of robots, whereas independent control policies do not exploit the information provided by other robots, exhibiting poor performance in cooperative-competitive tasks. In this work we propose a physics-informed reinforcement learning approach able to learn distributed multi-robot control policies that are both scalable and make use of all the available information to each robot. Our approach has three key characteristics. First, it imposes a port-Hamiltonian structure on the policy representation, respecting energy conservation properties of physical robot systems and the networked nature of robot team interactions. Second, it uses self-attention to ensure a sparse policy representation able to handle time-varying information at each robot from the interaction graph. Third, we present a soft actor-critic reinforcement learning algorithm parameterized by our self-attention port-Hamiltonian control policy, which accounts for the correlation among robots during training while overcoming the need of value function factorization. Extensive simulations in different multi-robot scenarios demonstrate the success of the proposed approach, surpassing previous multi-robot reinforcement learning solutions in scalability, while achieving similar or superior performance (with averaged cumulative reward up to x2 greater than the state-of-the-art with robot teams x6 larger than the number of robots at training time). We also validate our approach on multiple real robots in the Georgia Tech Robotarium under imperfect communication, demonstrating zero-shot sim-to-real transfer and scalability across number of robots.
View on arXiv@article{sebastian2025_2401.00212,
title={ Physics-Informed Multi-Agent Reinforcement Learning for Distributed Multi-Robot Problems },
author={ Eduardo Sebastian and Thai Duong and Nikolay Atanasov and Eduardo Montijano and Carlos Sagues },
journal={arXiv preprint arXiv:2401.00212},
year={ 2025 }
}