{"id":1773,"date":"2025-02-11T07:03:39","date_gmt":"2025-02-11T07:03:39","guid":{"rendered":"https:\/\/mailitics.com\/index.php\/2025\/02\/11\/2502-05706\/"},"modified":"2025-02-11T07:03:39","modified_gmt":"2025-02-11T07:03:39","slug":"2502-05706","status":"publish","type":"post","link":"https:\/\/mailitics.com\/index.php\/2025\/02\/11\/2502-05706\/","title":{"rendered":"TD(0) Learning converges for Polynomial mixing and non-linear functions"},"content":{"rendered":"<p>    TD(0) Learning converges for Polynomial mixing and non-linear functions<br \/>\n \t<BR><br \/>\n<BR><\/BR><br \/>\n    <!-- no image --><br \/>\n \t<BR><br \/>\n<BR><\/BR><\/p>\n<div>arXiv:2502.05706v1 Announce Type: new<br \/>\nAbstract: Theoretical work on Temporal Difference (TD) learning has provided finite-sample and high-probability guarantees for data generated from Markov chains. However, these bounds typically require linear function approximation, instance-dependent step sizes, algorithmic modifications, and restrictive mixing rates. We present theoretical findings for TD learning under more applicable assumptions, including instance-independent step sizes, full data utilization, and polynomial ergodicity, applicable to both linear and non-linear functions. textbf{To our knowledge, this is the first proof of TD(0) convergence on Markov data under universal and instance-independent step sizes.} While each contribution is significant on its own, their combination allows these bounds to be effectively utilized in practical application settings. Our results include bounds for linear models and non-linear under generalized gradients and H&#8221;older continuity.<\/div>\n<p> \t<BR><br \/>\n <BR><\/BR><br \/>\n    Anupama Sridhar, Alexander Johansen<br \/>\n \t<BR><br \/>\n<BR><\/BR><br \/>\n<a href=\"https:\/\/arxiv.org\/abs\/2502.05706\">Go to original source<\/a><br \/>\n \t<BR><br \/>\n <BR><\/BR><\/p>\n","protected":false},"excerpt":{"rendered":"<p>TD(0) Learning converges for Polynomial mixing and non-linear functions arXiv:2502.05706v1 Announce Type: new Abstract: Theoretical work on Temporal Difference (TD) learning has provided finite-sample and high-probability guarantees for data generated from Markov chains. However, these bounds typically require linear function approximation, instance-dependent step sizes, algorithmic modifications, and restrictive mixing rates. We present theoretical findings for [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[62,113,112],"tags":[199,496,1700],"class_list":["post-1773","post","type-post","status-publish","format-standard","hentry","category-aimldsaimlds","category-cs-lg","category-stat-ml","tag-learning","tag-linear","tag-td"],"_links":{"self":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/1773"}],"collection":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/comments?post=1773"}],"version-history":[{"count":0,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/1773\/revisions"}],"wp:attachment":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/media?parent=1773"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/categories?post=1773"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/tags?post=1773"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}