The mean-field framework has been used to find approximate solutions to problems involving very large populations of symmetric, anonymous agents, which may be intractable by other methods. The cooperative mean-field control (MFC) problem has received less attention than the non-cooperative mean-field game (MFG), despite the former potentially being more useful as a tool for engineering large-scale collective behaviours. Decentralised communication algorithms have recently been introduced to MFGs, giving benefits to learning speed and robustness. Inspired by this, we introduce networked communication to MFC - where populations arguably have broader incentive to communicate - and in particular to the setting where decentralised agents learn online from a single, non-episodic run of the empirical system. We adapt recent MFG algorithms to this new setting, as well as contributing a novel sub-routine allowing networked agents to estimate the global average reward from their local neighbourhood. Previous theoretical analysis of decentralised communication in MFGs does not extend trivially to MFC. We therefore contribute new theory proving that in MFC the networked communication scheme allows agents to increase social welfare faster than under both of the two typical alternative architectures, namely independent and centralised learning. We provide experiments that support this new result across different classes of cooperative game, and also give numerous ablation studies and additional experiments concerning numbers of communication round and robustness to communication failures.
COIN-GP: Cooperative Online Learning in Networked Distributed Systems with Partial Measurements via Gaussian Process Regression
Technical University of Munich(慕尼黑工业大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Tongji University(同济大学);Shanghai Yangzhi Rehabilitation Hospital(上海市养志康复医院);University of Science and Technology of China(中国科学技术大学);The Hong Kong Polytechnic University(香港理工大学)
Cooperative constrained motion coordination of networked heterogeneous vehicles
Eindhoven University of Technology(埃因霍温理工大学);Eindhoven Artificial Intelligence Systems Institute(埃因霍温人工智能系统研究所);Lund University(隆德大学);The Australian National University(澳大利亚国立大学)
An Infrastructure-less, Control-Independent Solution to Relative Localisation of a Team of Mobile Robots using Ranging Measurements
Department of Industrial Engineering, University of Trento(特伦托大学工业工程系);Department of Information Engineering and Computer Science, University of Trento(特伦托大学信息工程与计算机科学系)
Institute for Computer Science and Control, Hungarian Academy of Sciences(匈牙利科学院计算机科学与控制研究所);Faculty of Mechanical Engineering, Budapest University of Technology and Economics(布达佩斯技术与经济大学机械工程学院);Department of Health Care and Technology, KHLeuven(荷语鲁汶大学健康护理与技术系);LIMOS UMR 6158 CNRS, Ecole Nationale Supérieure des Mines de Saint-Etienne(圣艾蒂安国立高等矿业学院CNRS LIMOS联合研究实验室);Centre de Recherche en Automatique de Nancy (UMR 7039), Université de Lorraine, CNRS(洛林大学CNRS南西自动化研究中心);School of Electronic, Electrical and Computer Engineering, University of Birmingham(伯明翰大学电子、电气与计算机工程学院);Department of Control Systems Engineering, Gdansk University of Technology(格但斯克理工大学控制系统工程系)
Scalable Model-based Policy Optimization for Decentralized Networked Systems
Peking University(北京大学);Chinese Academy of Sciences(中国科学院);University College London(伦敦大学学院);King’s College London(伦敦国王学院);Xiamen University(厦门大学);BIGAI(北京通用人工智能研究院)