<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Policy Gradient |</title><link>https://aroraanshu26.github.io/tags/policy-gradient/</link><atom:link href="https://aroraanshu26.github.io/tags/policy-gradient/index.xml" rel="self" type="application/rss+xml"/><description>Policy Gradient</description><generator>HugoBlox Kit (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Thu, 30 Apr 2026 00:00:00 +0000</lastBuildDate><image><url>https://aroraanshu26.github.io/media/icon_hu_da05098ef60dc2e7.png</url><title>Policy Gradient</title><link>https://aroraanshu26.github.io/tags/policy-gradient/</link></image><item><title>Tracing the Roots: Trust Region Policy Optimization</title><link>https://aroraanshu26.github.io/publications/ds608/</link><pubDate>Thu, 30 Apr 2026 00:00:00 +0000</pubDate><guid>https://aroraanshu26.github.io/publications/ds608/</guid><description/></item></channel></rss>