<?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/" xmlns:memo="https://memo.d.foundation/ns/feed/1">
  <channel>
    <title>reinforcement-learning - Dwarves Memo</title>
    <atom:link href="https://memo.d.foundation/topics/applied-llm/tags/reinforcement-learning/rss.xml" rel="self" type="application/rss+xml" />
    <link>https://memo.d.foundation/topics/applied-llm/tags/reinforcement-learning</link>
    <description>The newest notes tagged reinforcement-learning on Dwarves Memo.</description>
    <lastBuildDate>Wed, 03 Jul 2024 00:00:00 GMT</lastBuildDate>
    <language>en-US</language>
    <sy:updatePeriod>hourly</sy:updatePeriod>
    <sy:updateFrequency>1</sy:updateFrequency>
    <item>
      <title>Proximal policy optimization</title>
      <link>https://memo.d.foundation/llm/proximal-policy-optimization</link>
      <pubDate>Wed, 03 Jul 2024 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[thanhpn]]></dc:creator>
      <description><![CDATA[Proximal policy optimization (PPO) is an algorithm that aims to improve the stability of training by avoiding overly large policy updates. It is a popular and effective method used for training [ reinforcement learning](#wikilink:Reinforcement%20Learning) models in complex environments. To achieve this, PPO uses a ratio that indicates the difference between the current policy and the old policy and clips this ratio within a specific range, ensuring that the policy updates are not too large and the training process is more stable...]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/llm/proximal-policy-optimization</guid>
    </item>
    <item>
      <title>Reward model</title>
      <link>https://memo.d.foundation/llm/reward-model</link>
      <pubDate>Fri, 23 Jun 2023 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[thanhpn]]></dc:creator>
      <description><![CDATA[A Reward model is a critical component in Reinforcement Learning for Large Language Models (LLMs), designed to evaluate and score the quality of generated responses. It plays a key role in aligning LLMs with human values and improving their output through iterative refinement.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/llm/reward-model</guid>
    </item>
    <item>
      <title>Introduction to reinforcement learning and its application with LLMs</title>
      <link>https://memo.d.foundation/llm/reinforcement-learning</link>
      <pubDate>Mon, 05 Jun 2023 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[thanhpn]]></dc:creator>
      <description><![CDATA[An introduction to Reinforcement Learning (RL), a machine learning method where an agent learns to make decisions by interacting with an environment. This article covers the basics of RL, including how it works, common algorithms, and its application in training models with Large Language Models (LLMs).]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/llm/reinforcement-learning</guid>
    </item>
  </channel>
</rss>