<?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>Talks on tjards</title>
    <link>https://r4lux.com/tags/talks/</link>
    <description>Recent content in Talks on tjards</description>
    <generator>Hugo -- 0.137.1</generator>
    <language>en-us</language>
    <lastBuildDate>Fri, 15 May 2026 13:31:41 -0400</lastBuildDate>
    <atom:link href="https://r4lux.com/tags/talks/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Invited Talk at Ingenuity Labs</title>
      <link>https://r4lux.com/posts/2026/rl_embeddings/</link>
      <pubDate>Fri, 15 May 2026 13:31:41 -0400</pubDate>
      <guid>https://r4lux.com/posts/2026/rl_embeddings/</guid>
      <description>&lt;p&gt;I recently had the pleasure of presenting our work at the 2026 &lt;a href=&#34;https://ingenuitylabs.queensu.ca/&#34;&gt;Ingenuity Labs Research Institute&lt;/a&gt; Multi-robots Workshop. We explored a central theme across our research: when integrated within a control-theoretic framework, machine learning can enhance the performance of physical systems while preserving formal guarantees of stability and robustness. Specifically, we discussed how the swarm embeddings proposed in our &lt;a href=&#34;https://doi.org/10.1016/j.automatica.2025.112221&#34;&gt;recent work&lt;/a&gt; can be reframed as equilibrium manifolds to ensure swarms can maintain coherence and stability while learning to adapt to their environment.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
