<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Reinforcement Learning on WorldSense Tech Blog</title><link>https://www.worldsensetech.com/en/tags/reinforcement-learning/</link><description>Recent content in Reinforcement Learning on WorldSense Tech Blog</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Tue, 25 Aug 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://www.worldsensetech.com/en/tags/reinforcement-learning/index.xml" rel="self" type="application/rss+xml"/><item><title>Understanding Dreamer: How World Models Learn to Imagine</title><link>https://www.worldsensetech.com/en/articles/2026-08-25-dreamer-explained/</link><pubDate>Tue, 25 Aug 2026 00:00:00 +0000</pubDate><guid>https://www.worldsensetech.com/en/articles/2026-08-25-dreamer-explained/</guid><description>&lt;blockquote&gt;
&lt;p&gt;&lt;strong&gt;Dreamer Series · Part 1&lt;/strong&gt;&lt;/p&gt;
&lt;p&gt;This article covers Dreamer&amp;rsquo;s overall architecture at a conceptual level. If you&amp;rsquo;ve already read the &lt;a href="https://www.worldsensetech.com/en/articles/2026-08-19-rssm-code-walkthrough/"&gt;RSSM Code Walkthrough Series&lt;/a&gt;, this article will help you connect the scattered code details into a coherent architectural understanding.&lt;/p&gt;
&lt;/blockquote&gt;
&lt;p&gt;Dreamer&amp;rsquo;s most important idea is not &amp;ldquo;training a model that generates future frames,&amp;rdquo; but rather &lt;strong&gt;training a latent world model sufficient to support decision-making, then letting policies learn inside that internal world.&lt;/strong&gt;&lt;/p&gt;</description></item></channel></rss>