Files
Varuna Jayasiri efd2673735 cleanup
2021-06-02 21:40:05 +05:30

149 lines
5.8 KiB
HTML

<!DOCTYPE html>
<html>
<head>
<meta http-equiv="content-type" content="text/html;charset=utf-8"/>
<meta name="viewport" content="width=device-width, initial-scale=1.0"/>
<meta name="description" content="This is a collection of PyTorch implementations/tutorials of reinforcement learning algorithms. It currently includes Proximal Policy Optimization, Generalized Advantage Estimation, and Deep Q Networks."/>
<meta name="twitter:card" content="summary"/>
<meta name="twitter:image:src" content="https://avatars1.githubusercontent.com/u/64068543?s=400&amp;v=4"/>
<meta name="twitter:title" content="Reinforcement Learning Algorithms"/>
<meta name="twitter:description" content="This is a collection of PyTorch implementations/tutorials of reinforcement learning algorithms. It currently includes Proximal Policy Optimization, Generalized Advantage Estimation, and Deep Q Networks."/>
<meta name="twitter:site" content="@labmlai"/>
<meta name="twitter:creator" content="@labmlai"/>
<meta property="og:url" content="https://nn.labml.ai/rl/index.html"/>
<meta property="og:title" content="Reinforcement Learning Algorithms"/>
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&amp;v=4"/>
<meta property="og:site_name" content="LabML Neural Networks"/>
<meta property="og:type" content="object"/>
<meta property="og:title" content="Reinforcement Learning Algorithms"/>
<meta property="og:description" content="This is a collection of PyTorch implementations/tutorials of reinforcement learning algorithms. It currently includes Proximal Policy Optimization, Generalized Advantage Estimation, and Deep Q Networks."/>
<title>Reinforcement Learning Algorithms</title>
<link rel="shortcut icon" href="/icon.png"/>
<link rel="stylesheet" href="../pylit.css">
<link rel="canonical" href="https://nn.labml.ai/rl/index.html"/>
<!-- Global site tag (gtag.js) - Google Analytics -->
<script async src="https://www.googletagmanager.com/gtag/js?id=G-4V3HC8HBLH"></script>
<script>
window.dataLayer = window.dataLayer || [];
function gtag() {
dataLayer.push(arguments);
}
gtag('js', new Date());
gtag('config', 'G-4V3HC8HBLH');
</script>
</head>
<body>
<div id='container'>
<div id="background"></div>
<div class='section'>
<div class='docs'>
<p>
<a class="parent" href="/">home</a>
<a class="parent" href="index.html">rl</a>
</p>
<p>
<a href="https://github.com/lab-ml/labml_nn/tree/master/labml_nn/rl/__init__.py">
<img alt="Github"
src="https://img.shields.io/github/stars/lab-ml/nn?style=social"
style="max-width:100%;"/></a>
<a href="https://twitter.com/labmlai"
rel="nofollow">
<img alt="Twitter"
src="https://img.shields.io/twitter/follow/labmlai?style=social"
style="max-width:100%;"/></a>
</p>
</div>
</div>
<div class='section' id='section-0'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-0'>#</a>
</div>
<h1>Reinforcement Learning Algorithms</h1>
<ul>
<li><a href="ppo">Proximal Policy Optimization</a><ul>
<li><a href="ppo/experiment.html">This is an experiment</a> that runs a PPO agent on Atari Breakout.</li>
<li><a href="ppo/gae.html">Generalized advantage estimation</a></li>
</ul>
</li>
<li><a href="dqn">Deep Q Networks</a><ul>
<li><a href="dqn/experiment.html">This is an experiment</a> that runs a DQN agent on Atari Breakout.</li>
<li><a href="dqn/model.html">Model</a> with dueling network</li>
<li><a href="dqn/replay_buffer.html">Prioritized Experience Replay Buffer</a></li>
</ul>
</li>
</ul>
<p><a href="game.html">This is the implementation for OpenAI game wrapper</a> using <code>multiprocessing</code>.</p>
</div>
<div class='code'>
<div class="highlight"><pre></pre></div>
</div>
</div>
</div>
</div>
<script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.4/MathJax.js?config=TeX-AMS_HTML">
</script>
<!-- MathJax configuration -->
<script type="text/x-mathjax-config">
MathJax.Hub.Config({
tex2jax: {
inlineMath: [ ['$','$'] ],
displayMath: [ ['$$','$$'] ],
processEscapes: true,
processEnvironments: true
},
// Center justify equations in code and markdown cells. Elsewhere
// we use CSS to left justify single line equations in code cells.
displayAlign: 'center',
"HTML-CSS": { fonts: ["TeX"] }
});
</script>
<script>
function handleImages() {
var images = document.querySelectorAll('p>img')
console.log(images);
for (var i = 0; i < images.length; ++i) {
handleImage(images[i])
}
}
function handleImage(img) {
img.parentElement.style.textAlign = 'center'
var modal = document.createElement('div')
modal.id = 'modal'
var modalContent = document.createElement('div')
modal.appendChild(modalContent)
var modalImage = document.createElement('img')
modalContent.appendChild(modalImage)
var span = document.createElement('span')
span.classList.add('close')
span.textContent = 'x'
modal.appendChild(span)
img.onclick = function () {
console.log('clicked')
document.body.appendChild(modal)
modalImage.src = img.src
}
span.onclick = function () {
document.body.removeChild(modal)
}
}
handleImages()
</script>
</body>
</html>