Koopman-Assisted Reinforcement Learning

[2403.02290] Koopman-Assisted Reinforcement Learning Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Artificial Intelligence arXiv:2403.02290 (cs) [Submitted on 4 Mar 2024 ( v1 ), last revised 1 May 2026 (this version, v2)] Title: Koopman-Assisted Reinforcement Learning Authors: Preston Rozwood , Edward Mehrez , Ludger Paehler , Wen Sun , Steven L. Brunton View a PDF of the paper titled Koopman-Assisted Reinforcement Learning, by Preston Rozwood and 4 other authors View PDF HTML (experimental) Abstract: The Bellman equation and its continuous form, the Hamilton-Jacobi-Bellman equation, are ubiquitous in reinforcement learning and control theory. However, these equations become intractable for high-dimensional or nonlinear systems. This paper develops two new reinforcement learning algorithms based on the data-driven Koopman operator, which lifts a nonlinear system into new coordinates where the dynamics become approximately linear, and where Hamilton-Jacobi-Bellman-based methods are more tractable. In particular, the Koopman operator captures the expectation of the time evolution of the value function via linear dynamics in the lifted coordinates. By parameterizing the Koopman operator with the control actions, we construct a ``controlled Koopman tensor'' that facilitates the estimation of the optimal value function. This enables us to reformulate two max-entropy RL algorithms: soft value iteration and soft actor-critic. This flexible and interpretable framework includes deterministic and stochastic systems, as well as discrete and continuous dynamics. Koopman Assisted reinforcement learning attains state-of-the-art performance with respect to traditional neural network-based soft actor-critic baselines on a linear state-space system, the Lorenz system, fluid flow past a cylinder, and a double-well potential with non-isotropic stochastic forcing. Comments: 28 pages, 10 figures, 4 tables Subjects: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG); Dynamical Systems (math.DS); Optimization and Control (math.OC) Cite as: arXiv:2403.02290 [cs.AI] (or arXiv:2403.02290v2 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2403.02290 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Ludger Paehler [ view email ] [v1] Mon, 4 Mar 2024 18:19:48 UTC (3,324 KB) [v2] Fri, 1 May 2026 05:16:59 UTC (4,692 KB) Full-text links: Access Paper: View a PDF of the paper titled Koopman-Assisted Reinforcement Learning, by Preston Rozwood and 4 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.AI < prev | next > new | recent | 2024-03 Change to browse by: cs cs.LG math math.DS math.OC References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Koopman-Assisted Reinforcement Learning#189179
• Koopman-Assisted Reinforcement Learning#189079
• Koopman-Assisted Reinforcement Learning#189029
• Survey on reinforcement learning for language processing#177664
• Survey on reinforcement learning for language processing#177184