Koopman Spectrum Nonlinear Regulators and Efficient Online Learning
University of Washington（华盛顿大学）；Ehime University（爱媛大学）；RIKEN Center for Advanced Intelligence Project（理化学研究所高级智能项目中心）；Et Cetera Robotics；Keio University（庆应义塾大学）；Harvard University（哈佛大学）；Osaka University（大阪大学）
Most modern reinforcement learning algorithms optimize a cumulative single-step cost along a trajectory. The optimized motions are often 'unnatural', representing, for example, behaviors with sudden accelerations that waste energy and lack predictability. In this work, we present a novel paradigm of controlling nonlinear systems via the minimization of the Koopman spectrum cost: a cost over the Koopman operator of the controlled dynamics. This induces a broader class of dynamical behaviors that evolve over stable manifolds such as nonlinear oscillators, closed loops, and smooth movements. We demonstrate that some dynamics characterizations that are not possible with a cumulative cost are feasible in this paradigm, which generalizes the classical eigenstructure and pole assignments to nonlinear decision making. Moreover, we present a sample efficient online learning algorithm for our problem that enjoys a sub-linear regret bound under some structural assumptions.
Nonparametric Sparse Online Learning of the Koopman Operator
Coordinated Science Laboratory, University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校协调科学实验室）；Department of Mathematics and Computer Science, Royal Military College of Canada（加拿大皇家军事学院数学与计算机科学系）；Department of Electrical and Computer Engineering, University at Albany, SUNY（纽约州立大学水牛城大学电气与计算机工程系）；Applied Physics Labs, Johns Hopkins University（约翰霍普金斯大学应用物理实验室）；Department of Electrical and Computer Engineering, Coordinated Science Laboratory, University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校电气与计算机工程系，协调科学实验室）
Deep Koopman Operator with Control for Nonlinear Systems
The Chinese University of Hong Kong（香港中文大学）；Southern University of Science and Technology（南方科技大学）；Shenzhen Research Institute of The Chinese University of Hong Kong（香港中文大学深圳研究院）
MAKO: Meta-Adaptive Koopman Operators for Learning-based Model Predictive Control of Parametrically Uncertain Nonlinear Systems
Water Research Institute (NEWRI), Nanyang Technological University, Singapore（新跃大学水研究 institute（NEWRI））；School of Chemistry, Chemical Engineering and Biotechnology, Nanyang Technological University, Singapore（新跃大学化学、化工与生物技术学院）；Soft Robotics Lab, ETH Zurich, Switzerland（苏黎世联邦理工学院软机器人实验室）；Department of Civil and Environmental Engineering, National University of Singapore, Singapore（新加坡国立大学土木与环境工程系）
School of Vehicle and Mobility, Tsinghua University（清华大学车辆与学院）；School of Mechanical Engineering, University of Science and Technology Beijing（北京科技大学机械工程学院）
Learning Decentralized Linear Quadratic Regulators with $\sqrt{T}$ Regret
School of Artificial Intelligence and Automation at the Huazhong University of Science and Technology（华中科技大学人工智能与自动化学院）；College of Petroleum Engineering, Yangtze University（长江大学石油工程学院）；Elmore Family School of Electrical and Computer Engineering at Purdue University（普渡大学埃尔莫尔家族电气与计算机工程学院）
