<?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>Continual Learning on Kevin Roice</title><link>https://www.kevinroice.com/tags/continual-learning/</link><description>Recent content in Continual Learning on Kevin Roice</description><generator>Hugo -- 0.128.0</generator><language>en</language><lastBuildDate>Sun, 03 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://www.kevinroice.com/tags/continual-learning/index.xml" rel="self" type="application/rss+xml"/><item><title>Position: Deployed Reinforcement Learning should be Continual</title><link>https://www.kevinroice.com/papers/paper3/</link><pubDate>Sat, 02 May 2026 00:00:00 +0000</pubDate><guid>https://www.kevinroice.com/papers/paper3/</guid><description>Many deployments are continual RL problems approximated as non-continual. We term these &amp;lsquo;measurable deployments&amp;rsquo;.</description></item></channel></rss>