{"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/value-function-approximation-via-low-rank","title":"Value function approximation via low-rank models","arxiv_id":"1509.00061","date":"2015-08-31","proceeding":null,"authors":["Hao Yi Ong"],"abstract":"We propose a novel value function approximation technique for Markov decision\nprocesses. We consider the problem of compactly representing the state-action\nvalue function using a low-rank and sparse matrix model. The problem is to\ndecompose a matrix that encodes the true value function into low-rank and\nsparse components, and we achieve this using Robust Principal Component\nAnalysis (PCA). Under minimal assumptions, this Robust PCA problem can be\nsolved exactly via the Principal Component Pursuit convex optimization problem.\nWe experiment the procedure on several examples and demonstrate that our method\nyields approximations essentially identical to the true function.","url_abs":"http://arxiv.org/abs/1509.00061v1","url_pdf":"http://arxiv.org/pdf/1509.00061v1.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":"value-function-approximation-via-low-rank","repo_url":"https://github.com/haoyio/LowRankMDP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[{"method_slug":"pca","method_name":"PCA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}