English
Related papers

Related papers: Koopman-Assisted Reinforcement Learning

200 papers

The discovery of linear embedding is the key to the synthesis of linear control techniques for nonlinear systems. In recent years, while Koopman operator theory has become a prominent approach for learning these linear embeddings through…

Robotics · Computer Science 2026-03-02 Rajpal Singh , Chandan Kumar Sah , Jishnu Keshavan

We develop a Koopman operator framework for studying the {computational properties} of dynamical systems. Specifically, we show that the resolvent of the Koopman operator provides a natural abstraction of halting, yielding a ``Koopman…

Mathematical Physics · Physics 2025-10-08 Francesco Caravelli , Jean-Charles Delvenne

Continuous-time reinforcement learning offers an appealing formalism for describing control problems in which the passage of time is not naturally divided into discrete increments. Here we consider the problem of predicting the distribution…

Machine Learning · Computer Science 2022-06-20 Harley Wiltzer , David Meger , Marc G. Bellemare

We present an approach to construct approximate Koopman-type decompositions for dynamical systems depending on static or time-varying parameters. Our method simultaneously constructs an invariant subspace and a parametric family of…

Optimization and Control · Mathematics 2024-11-12 Yue Guo , Milan Korda , Ioannis G. Kevrekidis , Qianxiao Li

Controlling nonlinear dynamical systems remains a central challenge in a wide range of applications, particularly when accurate first-principle models are unavailable. Data-driven approaches offer a promising alternative by designing…

Systems and Control · Electrical Eng. & Systems 2025-12-23 Robin Strässer , Karl Worthmann , Igor Mezić , Julian Berberich , Manuel Schaller , Frank Allgöwer

As autonomous systems become more ubiquitous in daily life, ensuring high performance with guaranteed safety is crucial. However, safety and performance could be competing objectives, which makes their co-optimization difficult.…

Robotics · Computer Science 2025-05-29 Manan Tayal , Aditya Singh , Shishir Kolathaya , Somil Bansal

Soft robotic manipulators offer operational advantage due to their compliant and deformable structures. However, their inherently nonlinear dynamics presents substantial challenges. Traditional analytical methods often depend on simplifying…

Robotics · Computer Science 2024-10-28 Uljad Berdica , Matthew Jackson , Niccolò Enrico Veronese , Jakob Foerster , Perla Maiolino

The Koopman operator provides a linear perspective on non-linear dynamics by focusing on the evolution of observables in an invariant subspace. Observables of interest are typically linearly reconstructed from the Koopman eigenfunctions.…

Dynamical Systems · Mathematics 2024-03-06 Shaowu Pan , Karthik Duraisamy

The Koopman operator framework can be used to identify a data-driven model of a nonlinear system. Unfortunately, when the data is corrupted by noise, the identified model can be biased. Additionally, depending on the choice of lifting…

Systems and Control · Electrical Eng. & Systems 2024-09-02 Louis Lortie , James Richard Forbes

The estimation for the region of attraction (ROA) of an asymptotically stable equilibrium point is crucial in the analysis of nonlinear systems. There has been a recent surge of interest in estimating the solution to Zubov's equation, whose…

Dynamical Systems · Mathematics 2024-06-28 Yiming Meng , Ruikun Zhou , Jun Liu

Bootstrapping and rollout are two fundamental principles for value function estimation in reinforcement learning (RL). We introduce a novel class of Bellman operators, called subgraph Bellman operators, that interpolate between…

Machine Learning · Computer Science 2024-12-02 Wenlong Mou , Jian Qian

The Koopman operator provides a powerful framework for modeling dynamical systems and has attracted growing interest from the machine learning community. However, its infinite-dimensional nature makes identifying suitable finite-dimensional…

Machine Learning · Computer Science 2026-02-05 Xiaoyuan Cheng , Wenxuan Yuan , Yiming Yang , Yuanzhao Zhang , Sibo Cheng , Yi He , Zhuo Sun

This paper presents a class of linear predictors for nonlinear controlled dynamical systems. The basic idea is to lift the nonlinear dynamics into a higher dimensional space where its evolution is approximately linear. In an uncontrolled…

Optimization and Control · Mathematics 2018-03-26 Milan Korda , Igor Mezić

A learning based method for obtaining feedback laws for nonlinear optimal control problems is proposed. The learning problem is posed such that the open loop value function is its optimal solution. This infinite dimensional, function space,…

Optimization and Control · Mathematics 2022-10-26 Karl Kunisch , Donato Vásquez-Varas , Daniel Walter

Classically, the optimal control problem in the presence of an adversary is formulated as a two-player zero-sum differential game or an $H_\infty$ control problem. The solution to these problems can be obtained by solving the…

Optimization and Control · Mathematics 2022-04-26 Alexander Krolicki , Sarang Sutavani , Umesh Vaidya

Koopman operators and transfer operators represent nonlinear dynamics in state space through its induced action on linear spaces of observables and measures, respectively. This framework enables the use of linear operator theory for…

Dynamical Systems · Mathematics 2025-06-06 Claire Valva , Dimitrios Giannakis

This work presents a data-driven Koopman operator-based modeling method using a model averaging technique. While the Koopman operator has been used for data-driven modeling and control of nonlinear dynamics, it is challenging to accurately…

Optimization and Control · Mathematics 2024-12-05 Daisuke Uchida , Karthik Duraisamy

Representation learning is critical to the empirical and theoretical success of reinforcement learning. However, many existing methods are induced from model-learning aspects, misaligning them with the RL task in hand. This work introduces…

Machine Learning · Computer Science 2026-02-03 Ofir Nabati , Bo Dai , Shie Mannor , Guy Tennenholtz

Many optimal control problems are formulated as two point boundary value problems (TPBVPs) with conditions of optimality derived from the Hamilton-Jacobi-Bellman (HJB) equations. In most cases, it is challenging to solve HJBs due to the…

Optimization and Control · Mathematics 2019-07-25 Sixiong You , Ran Dai , Ping Lu

Inverse reinforcement learning aims to infer the reward function that explains expert behavior observed through trajectories of state--action pairs. A long-standing difficulty in classical IRL is the non-uniqueness of the recovered reward:…

Machine Learning · Statistics 2025-12-09 Denis Belomestny , Alexey Naumov , Sergey Samsonov