<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>运动规划 on 朝花夕拾</title>
    <link>https://xwlu.github.io/tags/%E8%BF%90%E5%8A%A8%E8%A7%84%E5%88%92/</link>
    <description>Recent content in 运动规划 on 朝花夕拾</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Fri, 15 May 2026 14:43:15 +0800</lastBuildDate>
    <atom:link href="https://xwlu.github.io/tags/%E8%BF%90%E5%8A%A8%E8%A7%84%E5%88%92/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework</title>
      <link>https://xwlu.github.io/post/robotics/e2e/rad_2/</link>
      <pubDate>Fri, 24 Apr 2026 00:00:00 +0000</pubDate>
      <guid>https://xwlu.github.io/post/robotics/e2e/rad_2/</guid>
      <description>想象一下，你在教一个新手司机开车。用模仿学习（Imitation Learning）的方式，就像给他一大堆&amp;quot;老司机录像&amp;quot;反复看——他能学到很多驾驶技巧，但问题是，&lt;strong&gt;他只知道&amp;quot;该怎么开&amp;quot;，却从来没有为自己的失误付出过代价&lt;/strong&gt;。</description>
    </item>
  </channel>
</rss>
