<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Alberto Bernacchia | Learning And Signal Processing</title><link>https://lasp-ucl.github.io/author/alberto-bernacchia/</link><atom:link href="https://lasp-ucl.github.io/author/alberto-bernacchia/index.xml" rel="self" type="application/rss+xml"/><description>Alberto Bernacchia</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Wed, 01 Jan 2025 00:00:00 +0000</lastBuildDate><image><url>https://lasp-ucl.github.io/media/icon_hu488c70cfa50b07216f285734af4abcd1_22080_512x512_fill_lanczos_center_3.png</url><title>Alberto Bernacchia</title><link>https://lasp-ucl.github.io/author/alberto-bernacchia/</link></image><item><title>Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds</title><link>https://lasp-ucl.github.io/publication/dblp-conficml-kayal-vtsb-25/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://lasp-ucl.github.io/publication/dblp-conficml-kayal-vtsb-25/</guid><description>&lt;p>Add the &lt;strong>full text&lt;/strong> or &lt;strong>supplementary notes&lt;/strong> for the publication here using Markdown formatting.&lt;/p></description></item><item><title>Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds</title><link>https://lasp-ucl.github.io/publication/dblp-journalscorrabs-2505-23673/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://lasp-ucl.github.io/publication/dblp-journalscorrabs-2505-23673/</guid><description>&lt;p>Add the &lt;strong>full text&lt;/strong> or &lt;strong>supplementary notes&lt;/strong> for the publication here using Markdown formatting.&lt;/p></description></item><item><title>Near-Optimal Sample Complexity in Reward-Free Kernel-based Reinforcement Learning</title><link>https://lasp-ucl.github.io/publication/dblp-confaistats-kayal-vtb-25/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://lasp-ucl.github.io/publication/dblp-confaistats-kayal-vtb-25/</guid><description>&lt;p>Add the &lt;strong>full text&lt;/strong> or &lt;strong>supplementary notes&lt;/strong> for the publication here using Markdown formatting.&lt;/p></description></item><item><title>Near-Optimal Sample Complexity in Reward-Free Kernel-Based Reinforcement Learning</title><link>https://lasp-ucl.github.io/publication/dblp-journalscorrabs-2502-07715/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://lasp-ucl.github.io/publication/dblp-journalscorrabs-2502-07715/</guid><description>&lt;p>Add the &lt;strong>full text&lt;/strong> or &lt;strong>supplementary notes&lt;/strong> for the publication here using Markdown formatting.&lt;/p></description></item><item><title>Reinforcement Learning Using known Invariances</title><link>https://lasp-ucl.github.io/publication/dblp-journalscorrabs-2511-03473/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://lasp-ucl.github.io/publication/dblp-journalscorrabs-2511-03473/</guid><description>&lt;p>Add the &lt;strong>full text&lt;/strong> or &lt;strong>supplementary notes&lt;/strong> for the publication here using Markdown formatting.&lt;/p></description></item></channel></rss>