<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
	<channel>
		<title>Reinforcement on Alok Regmi</title>
		<link>https://alokregmi.com/tags/reinforcement/</link>
		<description>Recent content in Reinforcement on Alok Regmi</description>
		<generator>Hugo</generator>
		<language>en-us</language>
		
		
		
		
			<lastBuildDate>Sat, 02 May 2020 03:46:03 +0545</lastBuildDate>
		
			<atom:link href="https://alokregmi.com/tags/reinforcement/index.xml" rel="self" type="application/rss+xml" />
			<item>
				<title>MUZero</title>
				<link>https://alokregmi.com/braindump/2020/04/muzero/</link>
				<pubDate>Sun, 19 Apr 2020 15:59:20 +0545</pubDate>
				<guid>https://alokregmi.com/braindump/2020/04/muzero/</guid>
				<description>&lt;p&gt;MuZero:&lt;/p&gt;&#xA;&lt;p&gt;&amp;ndash; Works based on AlphaZero&amp;rsquo;s search and planning space&#xA;&amp;ndash; Learns optimal policy, reward functions, value functions automatically&#xA;&amp;ndash; The main idea of the algorithm is to predict those aspects of the future that are directly&#xA;relevant for planning.&#xA;&amp;ndash; Observation image ===&amp;gt; Model ==&amp;gt; Encodes to hidden states ==&amp;gt; Hidden states updated using&#xA;previous step&amp;rsquo;s hidden state and hypothetical next action&#xA;&amp;ndash; In each step, model predicts value fn, optimal policy, and immediate reward&lt;/p&gt;</description>
			</item>
			<item>
				<title>MUZero</title>
				<link>https://alokregmi.com/ai/muzero/</link>
				<pubDate>Wed, 15 Apr 2020 00:00:00 +0000</pubDate>
				<guid>https://alokregmi.com/ai/muzero/</guid>
				<description>&lt;p&gt;MuZero:&lt;/p&gt;&#xA;&lt;p&gt;&amp;ndash; Works based on AlphaZero&amp;rsquo;s search and planning space&#xA;&amp;ndash; Learns optimal policy, reward functions, value functions automatically&#xA;&amp;ndash; The main idea of the algorithm is to predict those aspects of the future that are directly&#xA;relevant for planning.&#xA;&amp;ndash; Observation image ===&amp;gt; Model ==&amp;gt; Encodes to hidden states ==&amp;gt; Hidden states updated using&#xA;previous step&amp;rsquo;s hidden state and hypothetical next action&#xA;&amp;ndash; In each step, model predicts value fn, optimal policy, and immediate reward&lt;/p&gt;</description>
			</item>
	</channel>
</rss>
