<?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>Building-Automation on Cognaptus</title>
    <link>https://cognaptus.com/tags/building-automation/</link>
    <description>Recent content in Building-Automation on Cognaptus</description>
    <generator>Hugo -- 0.145.0</generator>
    <language>en-us</language>
    <lastBuildDate>Tue, 06 Jan 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://cognaptus.com/tags/building-automation/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Jerk Matters: Teaching Reinforcement Learning Some Mechanical Manners</title>
      <link>https://cognaptus.com/blog/2026-01-06-jerk-matters-teaching-reinforcement-learning-some-mechanical-manners/</link>
      <pubDate>Tue, 06 Jan 2026 00:00:00 +0000</pubDate>
      <guid>https://cognaptus.com/blog/2026-01-06-jerk-matters-teaching-reinforcement-learning-some-mechanical-manners/</guid>
      <description>A mechanism-first reading of how higher-order action regularization can make reinforcement learning policies smoother, less switch-happy, and more practical for HVAC and other physical-control systems.</description>
    </item>
    <item>
      <title>When Your House Talks Back: Teaching Buildings to Think About Energy</title>
      <link>https://cognaptus.com/blog/2026-01-01-when-your-house-talks-back-teaching-buildings-to-think-about-energy/</link>
      <pubDate>Thu, 01 Jan 2026 00:00:00 +0000</pubDate>
      <guid>https://cognaptus.com/blog/2026-01-01-when-your-house-talks-back-teaching-buildings-to-think-about-energy/</guid>
      <description>A smart-building benchmark shows why LLM agents are already useful for grounded device operations—and why financial reasoning still belongs behind deterministic controls.</description>
    </item>
  </channel>
</rss>
