<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	>

<channel>
	<title>MuJoCo &#8211; BIOENGINEER.ORG</title>
	<atom:link href="https://bioengineer.org/tag/mujoco/feed/" rel="self" type="application/rss+xml" />
	<link>https://bioengineer.org</link>
	<description>Bioengineering</description>
	<lastBuildDate>Thu, 08 Oct 2026 05:33:21 +0000</lastBuildDate>
	<language>en-US</language>
	<sy:updatePeriod>
	hourly	</sy:updatePeriod>
	<sy:updateFrequency>
	1	</sy:updateFrequency>
	<generator>https://wordpress.org/?v=7.1.3</generator>

<image>
	<url>https://bioengineer.org/wp-content/uploads/2019/09/cropped-bioengineering-32x32.png</url>
	<title>MuJoCo &#8211; BIOENGINEER.ORG</title>
	<link>https://bioengineer.org</link>
	<width>32</width>
	<height>32</height>
</image> 
<site xmlns="com-wordpress:feed-additions:1">72741379</site>	<item>
		<title>Contrastive Learning Tames Out-of-Distribution Actions in Offline Reinforcement Learning</title>
		<link>https://bioengineer.org/contrastive-learning-tames-out-of-distribution-actions-in-offline-reinforcement-learning/</link>
		
		<dc:creator><![CDATA[]]></dc:creator>
		<pubDate>Thu, 08 Oct 2026 05:33:21 +0000</pubDate>
				<category><![CDATA[Technology]]></category>
		<category><![CDATA[actor-critic]]></category>
		<category><![CDATA[Adroit]]></category>
		<category><![CDATA[contrastive learning]]></category>
		<category><![CDATA[D4RL benchmark]]></category>
		<category><![CDATA[distribution shift]]></category>
		<category><![CDATA[Machine Learning]]></category>
		<category><![CDATA[MuJoCo]]></category>
		<category><![CDATA[offline reinforcement learning]]></category>
		<category><![CDATA[out-of-distribution actions]]></category>
		<category><![CDATA[representation learning]]></category>
		<category><![CDATA[TD3+BC]]></category>
		<category><![CDATA[value overestimation]]></category>
		<guid isPermaLink="false">https://bioengineer.org/?p=406869</guid>

					<description><![CDATA[Researchers at Hanyang University have developed TACCO, a contrastive learning method that explicitly identifies and suppresses out-of-distribution actions to stabilize offline reinforcement learning across dense and sparse reward benchmarks.]]></description>
		
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">406869</post-id>	</item>
	</channel>
</rss>
