<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Games on skulldc</title><link>https://skulldc.net/tags/games/</link><description>Recent content in Games on skulldc</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 16 Nov 2026 10:26:00 +0000</lastBuildDate><atom:link href="https://skulldc.net/tags/games/index.xml" rel="self" type="application/rss+xml"/><item><title>Gamer trains one vision-language-action model to play 2D and 3D games in real time</title><link>https://skulldc.net/2026/11/gamer-trains-one-vision-language-action-model-to-play-2d-and-3d-games/</link><pubDate>Mon, 16 Nov 2026 10:26:00 +0000</pubDate><guid>https://skulldc.net/2026/11/gamer-trains-one-vision-language-action-model-to-play-2d-and-3d-games/</guid><description>A 27-author paper describes Gamer, an agent pre-trained on tens of thousands of hours of keyboard and mouse trajectories, then tuned with sparse thinking and multi-turn reinforcement learning for long-horizon play.</description></item></channel></rss>