<?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>Exit Code: 0</title><link>https://stefanciutac.github.io/stefanciutac_devlog/</link><description>Recent content on Exit Code: 0</description><generator>Hugo -- 0.153.2</generator><language>en-gb</language><lastBuildDate>Wed, 01 Apr 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://stefanciutac.github.io/stefanciutac_devlog/index.xml" rel="self" type="application/rss+xml"/><item><title>evoNN_UTTT v0.1</title><link>https://stefanciutac.github.io/stefanciutac_devlog/posts/evonn_uttt-v0.1/</link><pubDate>Wed, 01 Apr 2026 00:00:00 +0000</pubDate><guid>https://stefanciutac.github.io/stefanciutac_devlog/posts/evonn_uttt-v0.1/</guid><description>&lt;h3 id="introduction"&gt;&lt;strong&gt;Introduction&lt;/strong&gt;&lt;/h3&gt;
&lt;p&gt;It&amp;rsquo;s 2026. I shouldn&amp;rsquo;t need to exert myself having fun playing board games when a computer can have fun for me. Enter: &lt;em&gt;evoNN-uttt&lt;/em&gt; — a neural network trained to beat me at the game of &amp;lsquo;Ultimate Tic-Tac-Toe&amp;rsquo;.&lt;/p&gt;
&lt;p&gt;Aside from some brief experiments conducted a few months ago (consisting of optimising hyperparameters for a genetic algorithm that solved the pure knapsack problem), I do not have much experience with evolutionary algorithms (note: I will use the terms &lt;em&gt;evolutionary algorithm&lt;/em&gt; and &lt;em&gt;genetic algorithm&lt;/em&gt; interchangeably), so iterating on and optimising a library for running the algorithm efficiently should be an interesting learning experience.&lt;/p&gt;</description></item></channel></rss>