162315 20251017144612.0 doi 10.1109/TRO.2025.3582836 sideral 144882 ART-2025-144882 eng Sebastián, Eduardo Universidad de Zaragoza (orcid)0000-0001-9671-4056 Physics-Informed Multiagent Reinforcement Learning for Distributed Multirobot Problems 2025 Access copy available to the general public Unrestricted The networked nature of multirobot systems presents challenges in the context of multiagent 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 multirobot 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 multirobot scenarios demonstrate the success of the proposed approach, surpassing previous multirobot reinforcement learning solutions in scalability, while achieving similar or superior performance (with averaged cumulative reward up to ×2 greater than the state-of-the-art with robot teams ×6 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. info:eu-repo/grantAgreement/EUR/AEI/TED2021-130224B-I00 info:eu-repo/grantAgreement/ES/DGA/T45-23R info:eu-repo/grantAgreement/ES/MCIU/FPU19-05700 info:eu-repo/grantAgreement/ES/MICINN/PID2021-125514NB-I00 info:eu-repo/semantics/openAccess by https://creativecommons.org/licenses/by/4.0/deed.es info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion Duong, Thai Atanasov, Nikolay Montijano, Eduardo Universidad de Zaragoza (orcid)0000-0002-5176-3767 Sagüés, Carlos Universidad de Zaragoza (orcid)0000-0002-3032-954X 5007 520 Universidad de Zaragoza Dpto. Informát.Ingenie.Sistms. Área Ingen.Sistemas y Automát. 41 (2025), 4499-4517 IEEE Trans. Robot. IEEE Transactions on Robotics 1552-3098 The supplementary video is a supporting document to the article 10.1109/TRO.2025.3582836/mm1 10604245 http://zaguan.unizar.es/record/162315/files/texto_completo.pdf Versión publicada 3651467 http://zaguan.unizar.es/record/162315/files/texto_completo.jpg?subformat=icon icon Versión publicada oai:zaguan.unizar.es:162315 articulos driver 2025-10-17-14:17:57 ARTICLE