{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/an-efficient-expressive-and-local-minima-free","title":"An Efficient, Expressive and Local Minima-free Method for Learning Controlled Dynamical Systems","arxiv_id":"1702.03537","date":"2017-02-12","proceeding":null,"authors":["Ahmed Hefny","Carlton Downey","Geoffrey J. Gordon"],"abstract":"We propose a framework for modeling and estimating the state of controlled\ndynamical systems, where an agent can affect the system through actions and\nreceives partial observations. Based on this framework, we propose the\nPredictive State Representation with Random Fourier Features (RFFPSR). A key\nproperty in RFF-PSRs is that the state estimate is represented by a conditional\ndistribution of future observations given future actions. RFF-PSRs combine this\nrepresentation with moment-matching, kernel embedding and local optimization to\nachieve a method that enjoys several favorable qualities: It can represent\ncontrolled environments which can be affected by actions; it has an efficient\nand theoretically justified learning algorithm; it uses a non-parametric\nrepresentation that has expressive power to represent continuous non-linear\ndynamics. We provide a detailed formulation, a theoretical analysis and an\nexperimental evaluation that demonstrates the effectiveness of our method.","url_abs":"http://arxiv.org/abs/1702.03537v2","url_pdf":"http://arxiv.org/pdf/1702.03537v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"an-efficient-expressive-and-local-minima-free","repo_url":"https://github.com/ahefnycmu/rffpsr","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}