<?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>Reinforcement-Learning on nmnhut</title><link>https://nmnhut.dev/tags/reinforcement-learning/</link><description>Recent content in Reinforcement-Learning on nmnhut</description><generator>Hugo -- 0.157.0</generator><language>en-us</language><lastBuildDate>Thu, 25 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://nmnhut.dev/tags/reinforcement-learning/index.xml" rel="self" type="application/rss+xml"/><item><title>CTDE and MAPPO: A Plain Guide to Multi-Agent Reinforcement Learning</title><link>https://nmnhut.dev/posts/ctde-mappo-multi-agent-rl/</link><pubDate>Thu, 25 Jun 2026 00:00:00 +0000</pubDate><guid>https://nmnhut.dev/posts/ctde-mappo-multi-agent-rl/</guid><description>What CTDE and MAPPO mean in multi-agent reinforcement learning, which papers to cite, and how hard those papers are to reproduce — including whether you can do it on a CPU.</description></item></channel></rss>