<!DOCTYPE html> <html> <head> <meta charset="utf-8" /> <meta name="author" content="Brandon Rozek"> <meta name="viewport" content="width=device-width, initial-scale=1.0"> <meta name="robots" content="noindex" /> <title>Brandon Rozek</title> <link rel="stylesheet" href="themes/bitsandpieces/styles/main.css" type="text/css" /> <link rel="stylesheet" href="themes/bitsandpieces/styles/highlightjs-github.css" type="text/css" /> </head> <body> <aside class="main-nav"> <nav> <ul> <li class="menuitem "> <a href="index.html%3Findex.html" data-shortcut=""> Home </a> </li> <li class="menuitem "> <a href="index.html%3Fcourses.html" data-shortcut=""> Courses </a> </li> <li class="menuitem "> <a href="index.html%3Flabaide.html" data-shortcut=""> Lab Aide </a> </li> <li class="menuitem "> <a href="index.html%3Fpresentations.html" data-shortcut=""> Presentations </a> </li> <li class="menuitem "> <a href="index.html%3Fresearch.html" data-shortcut=""> Research </a> </li> <li class="menuitem "> <a href="index.html%3Ftranscript.html" data-shortcut=""> Transcript </a> </li> </ul> </nav> </aside> <main class="main-content"> <article class="article"> <h1>Reinforcement Learning</h1> <p>Reinforcement learning is the art of analyzing situations and mapping them to actions in order to maximize a numerical reward signal.</p> <p>In this independent study, I as well as Dr. Stephen Davies, will explore the Reinforcement Learning problem and its subproblems. We will go over the bandit problem, markov decision processes, and discover how best to translate a problem in order to <strong>make decisions</strong>.</p> <p>I have provided a list of topics that I wish to explore in a <a href="index.html%3Fresearch%252FReinforcementLearning%252Fsyllabus.html">syllabus</a></p> <h2>Readings</h2> <p>In order to spend more time learning, I decided to follow a textbook this time. </p> <p>Reinforcement Learning: An Introduction</p> <p>By Richard S. Sutton and Andrew G. Barto</p> <p><a href="index.html%3Fresearch%252FReinforcementLearning%252Freadings.html">Reading Schedule</a> </p> <h2>Notes</h2> <p>The notes for this course, is going to be an extreemly summarized version of the textbook. There will also be notes on whatever side tangents Dr. Davies and I explore.</p> <p><a href="index.html%3Fresearch%252FReinforcementLearning%252Fnotes.html">Notes page</a></p> <p>I wrote a small little quirky/funny report describing the bandit problem. Great for learning about the common considerations for Reinforcement Learning problems.</p> <p><a href="/files/research/TheBanditReport.pdf">The Bandit Report</a></p> <h2>Code</h2> <p>Code will occasionally be written to solidify the learning material and to act as aids for more exploration. </p> <p><a href="https://github.com/brandon-rozek/ReinforcementLearning">Github Link</a></p> <p>Specifically, if you want to see agents I've created to solve some OpenAI environments, take a look at this specific folder in the Github Repository</p> <p><a href="https://github.com/Brandon-Rozek/ReinforcementLearning/tree/master/agents">Github Link</a></p> </article> </main> <script src="themes/bitsandpieces/scripts/highlight.js"></script> <script src="themes/bitsandpieces/scripts/mousetrap.min.js"></script> <script type="text/x-mathjax-config"> MathJax.Hub.Config({ tex2jax: { inlineMath: [ ['$','$'], ["\\(","\\)"] ], processEscapes: true } }); </script> <script type="text/javascript" src="http://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML"> </script> <script> hljs.initHighlightingOnLoad(); document.querySelectorAll('.menuitem a').forEach(function(el) { if (el.getAttribute('data-shortcut').length > 0) { Mousetrap.bind(el.getAttribute('data-shortcut'), function() { location.assign(el.getAttribute('href')); }); } }); </script> </body> </html>