<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>On-Policy-Learning on Cognaptus</title>
    <link>https://cognaptus.com/tags/on-policy-learning/</link>
    <description>Recent content in On-Policy-Learning on Cognaptus</description>
    <generator>Hugo -- 0.145.0</generator>
    <language>en-us</language>
    <lastBuildDate>Mon, 16 Nov 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://cognaptus.com/tags/on-policy-learning/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>The Teacher&#39;s Trace Is Not a Training Target</title>
      <link>https://cognaptus.com/blog/2026-11-16-the-teachers-trace-is-not-a-training-target/</link>
      <pubDate>Mon, 16 Nov 2026 00:00:00 +0000</pubDate>
      <guid>https://cognaptus.com/blog/2026-11-16-the-teachers-trace-is-not-a-training-target/</guid>
      <description>How Bridged Self-Distillation uses external AI reasoning to improve smaller models without copying teacher responses or requiring teacher token probabilities.</description>
    </item>
  </channel>
</rss>
