mhjensen
413 lines
19 KiB
HTML
413 lines
19 KiB
HTML
<!DOCTYPE html>
|
|
|
|
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
|
|
<meta name="generator" content="DocOnce: https://github.com/hplgit/doconce/" />
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
|
<meta name="description" content="Data Analysis and Machine Learning: Reinforcement Learning">
|
|
|
|
<title>Data Analysis and Machine Learning: Reinforcement Learning</title>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<!-- reveal.js: http://lab.hakim.se/reveal-js/ -->
|
|
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0, maximum-scale=1.0, user-scalable=no">
|
|
|
|
<meta name="apple-mobile-web-app-capable" content="yes" />
|
|
<meta name="apple-mobile-web-app-status-bar-style" content="black-translucent" />
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0, maximum-scale=1.0, user-scalable=no, minimal-ui">
|
|
|
|
<link rel="stylesheet" href="reveal.js/css/reveal.css">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/beige.css" id="theme">
|
|
<!--
|
|
<link rel="stylesheet" href="reveal.js/css/reveal.css">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/beige.css" id="theme">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/beigesmall.css" id="theme">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/solarized.css" id="theme">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/serif.css" id="theme">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/night.css" id="theme">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/moon.css" id="theme">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/simple.css" id="theme">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/sky.css" id="theme">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/darkgray.css" id="theme">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/default.css" id="theme">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/cbc.css" id="theme">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/simula.css" id="theme">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/black.css" id="theme">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/white.css" id="theme">
|
|
<link rel="stylesheet" href="reveal.js/css/theme/league.css" id="theme">
|
|
-->
|
|
|
|
<!-- For syntax highlighting -->
|
|
<link rel="stylesheet" href="reveal.js/lib/css/zenburn.css">
|
|
|
|
<!-- Printing and PDF exports -->
|
|
<script>
|
|
var link = document.createElement( 'link' );
|
|
link.rel = 'stylesheet';
|
|
link.type = 'text/css';
|
|
link.href = window.location.search.match( /print-pdf/gi ) ? 'css/print/pdf.css' : 'css/print/paper.css';
|
|
document.getElementsByTagName( 'head' )[0].appendChild( link );
|
|
</script>
|
|
|
|
<style type="text/css">
|
|
hr { border: 0; width: 80%; border-bottom: 1px solid #aaa}
|
|
p.caption { width: 80%; font-size: 60%; font-style: italic; text-align: left; }
|
|
hr.figure { border: 0; width: 80%; border-bottom: 1px solid #aaa}
|
|
.reveal .alert-text-small { font-size: 80%; }
|
|
.reveal .alert-text-large { font-size: 130%; }
|
|
.reveal .alert-text-normal { font-size: 90%; }
|
|
.reveal .alert {
|
|
padding:8px 35px 8px 14px; margin-bottom:18px;
|
|
text-shadow:0 1px 0 rgba(255,255,255,0.5);
|
|
border:5px solid #bababa;
|
|
-webkit-border-radius: 14px; -moz-border-radius: 14px;
|
|
border-radius:14px;
|
|
background-position: 10px 10px;
|
|
background-repeat: no-repeat;
|
|
background-size: 38px;
|
|
padding-left: 30px; /* 55px; if icon */
|
|
}
|
|
.reveal .alert-block {padding-top:14px; padding-bottom:14px}
|
|
.reveal .alert-block > p, .alert-block > ul {margin-bottom:1em}
|
|
/*.reveal .alert li {margin-top: 1em}*/
|
|
.reveal .alert-block p+p {margin-top:5px}
|
|
/*.reveal .alert-notice { background-image: url(http://hplgit.github.io/doconce/bundled/html_images/small_gray_notice.png); }
|
|
.reveal .alert-summary { background-image:url(http://hplgit.github.io/doconce/bundled/html_images/small_gray_summary.png); }
|
|
.reveal .alert-warning { background-image: url(http://hplgit.github.io/doconce/bundled/html_images/small_gray_warning.png); }
|
|
.reveal .alert-question {background-image:url(http://hplgit.github.io/doconce/bundled/html_images/small_gray_question.png); } */
|
|
|
|
</style>
|
|
|
|
|
|
|
|
<!-- Styles for table layout of slides -->
|
|
<style type="text/css">
|
|
td.padding {
|
|
padding-top:20px;
|
|
padding-bottom:20px;
|
|
padding-right:50px;
|
|
padding-left:50px;
|
|
}
|
|
</style>
|
|
|
|
</head>
|
|
|
|
<body>
|
|
<div class="reveal">
|
|
|
|
<!-- Any section element inside the <div class="slides"> container
|
|
is displayed as a slide -->
|
|
|
|
<div class="slides">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<section>
|
|
<!-- ------------------- main content ---------------------- -->
|
|
|
|
|
|
|
|
<center><h1 style="text-align: center;">Data Analysis and Machine Learning: Reinforcement Learning </h1></center> <!-- document title -->
|
|
|
|
<p>
|
|
<!-- author(s): Morten Hjorth-Jensen -->
|
|
|
|
<center>
|
|
<b>Morten Hjorth-Jensen</b> [1, 2]
|
|
</center>
|
|
|
|
<p> <br>
|
|
<!-- institution(s) -->
|
|
|
|
<center>[1] <b>Department of Physics, University of Oslo</b></center>
|
|
<center>[2] <b>Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University</b></center>
|
|
<br>
|
|
<p> <br>
|
|
<center><h4>Dec 26, 2018</h4></center> <!-- date -->
|
|
<br>
|
|
<p>
|
|
|
|
<center style="font-size:80%">
|
|
<!-- copyright --> © 1999-2018, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
|
|
</center>
|
|
</section>
|
|
|
|
|
|
<section>
|
|
<h2 id="___sec0">Reinforcement Learning: Overarching view </h2>
|
|
|
|
<p>
|
|
Reinforcement Learning (RL) is one of the most exciting fields of Machine Learning today, and also one
|
|
of the oldest. It has been around since the 1950s, producing many interesting applications over the years.
|
|
</section>
|
|
|
|
|
|
<section>
|
|
<h2 id="___sec1">Code example </h2>
|
|
<p>
|
|
|
|
<!-- code=python (!bc pycod) typeset with pygments style "perldoc" -->
|
|
<div class="highlight" style="background: #eeeedd"><pre style="font-size: 80%; line-height: 125%"><span></span><span style="color: #CD5555">"""</span>
|
|
<span style="color: #CD5555">A simple example for Reinforcement Learning using table lookup Q-learning method.</span>
|
|
<span style="color: #CD5555">An agent "o" is on the left of a 1 dimensional world, the treasure is on the rightmost location.</span>
|
|
<span style="color: #CD5555">Run this program and to see how the agent will improve its strategy of finding the treasure.</span>
|
|
<span style="color: #CD5555">View more on my tutorial page: https://morvanzhou.github.io/tutorials/</span>
|
|
<span style="color: #CD5555">"""</span>
|
|
|
|
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">numpy</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">np</span>
|
|
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">pandas</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">pd</span>
|
|
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">time</span>
|
|
|
|
np.random.seed(<span style="color: #B452CD">2</span>) <span style="color: #228B22"># reproducible</span>
|
|
|
|
|
|
N_STATES = <span style="color: #B452CD">6</span> <span style="color: #228B22"># the length of the 1 dimensional world</span>
|
|
ACTIONS = [<span style="color: #CD5555">'left'</span>, <span style="color: #CD5555">'right'</span>] <span style="color: #228B22"># available actions</span>
|
|
EPSILON = <span style="color: #B452CD">0.9</span> <span style="color: #228B22"># greedy police</span>
|
|
ALPHA = <span style="color: #B452CD">0.1</span> <span style="color: #228B22"># learning rate</span>
|
|
GAMMA = <span style="color: #B452CD">0.9</span> <span style="color: #228B22"># discount factor</span>
|
|
MAX_EPISODES = <span style="color: #B452CD">13</span> <span style="color: #228B22"># maximum episodes</span>
|
|
FRESH_TIME = <span style="color: #B452CD">0.3</span> <span style="color: #228B22"># fresh time for one move</span>
|
|
|
|
|
|
<span style="color: #8B008B; font-weight: bold">def</span> <span style="color: #008b45">build_q_table</span>(n_states, actions):
|
|
table = pd.DataFrame(
|
|
np.zeros((n_states, <span style="color: #658b00">len</span>(actions))), <span style="color: #228B22"># q_table initial values</span>
|
|
columns=actions, <span style="color: #228B22"># actions's name</span>
|
|
)
|
|
<span style="color: #228B22"># print(table) # show table</span>
|
|
<span style="color: #8B008B; font-weight: bold">return</span> table
|
|
|
|
|
|
<span style="color: #8B008B; font-weight: bold">def</span> <span style="color: #008b45">choose_action</span>(state, q_table):
|
|
<span style="color: #228B22"># This is how to choose an action</span>
|
|
state_actions = q_table.iloc[state, :]
|
|
<span style="color: #8B008B; font-weight: bold">if</span> (np.random.uniform() > EPSILON) <span style="color: #8B008B">or</span> ((state_actions == <span style="color: #B452CD">0</span>).all()): <span style="color: #228B22"># act non-greedy or state-action have no value</span>
|
|
action_name = np.random.choice(ACTIONS)
|
|
<span style="color: #8B008B; font-weight: bold">else</span>: <span style="color: #228B22"># act greedy</span>
|
|
action_name = state_actions.idxmax() <span style="color: #228B22"># replace argmax to idxmax as argmax means a different function in newer version of pandas</span>
|
|
<span style="color: #8B008B; font-weight: bold">return</span> action_name
|
|
|
|
|
|
<span style="color: #8B008B; font-weight: bold">def</span> <span style="color: #008b45">get_env_feedback</span>(S, A):
|
|
<span style="color: #228B22"># This is how agent will interact with the environment</span>
|
|
<span style="color: #8B008B; font-weight: bold">if</span> A == <span style="color: #CD5555">'right'</span>: <span style="color: #228B22"># move right</span>
|
|
<span style="color: #8B008B; font-weight: bold">if</span> S == N_STATES - <span style="color: #B452CD">2</span>: <span style="color: #228B22"># terminate</span>
|
|
S_ = <span style="color: #CD5555">'terminal'</span>
|
|
R = <span style="color: #B452CD">1</span>
|
|
<span style="color: #8B008B; font-weight: bold">else</span>:
|
|
S_ = S + <span style="color: #B452CD">1</span>
|
|
R = <span style="color: #B452CD">0</span>
|
|
<span style="color: #8B008B; font-weight: bold">else</span>: <span style="color: #228B22"># move left</span>
|
|
R = <span style="color: #B452CD">0</span>
|
|
<span style="color: #8B008B; font-weight: bold">if</span> S == <span style="color: #B452CD">0</span>:
|
|
S_ = S <span style="color: #228B22"># reach the wall</span>
|
|
<span style="color: #8B008B; font-weight: bold">else</span>:
|
|
S_ = S - <span style="color: #B452CD">1</span>
|
|
<span style="color: #8B008B; font-weight: bold">return</span> S_, R
|
|
|
|
|
|
<span style="color: #8B008B; font-weight: bold">def</span> <span style="color: #008b45">update_env</span>(S, episode, step_counter):
|
|
<span style="color: #228B22"># This is how environment be updated</span>
|
|
env_list = [<span style="color: #CD5555">'-'</span>]*(N_STATES-<span style="color: #B452CD">1</span>) + [<span style="color: #CD5555">'T'</span>] <span style="color: #228B22"># '---------T' our environment</span>
|
|
<span style="color: #8B008B; font-weight: bold">if</span> S == <span style="color: #CD5555">'terminal'</span>:
|
|
interaction = <span style="color: #CD5555">'Episode %s: total_steps = %s'</span> % (episode+<span style="color: #B452CD">1</span>, step_counter)
|
|
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">'\r{}'</span>.format(interaction), end=<span style="color: #CD5555">''</span>)
|
|
time.sleep(<span style="color: #B452CD">2</span>)
|
|
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">'\r '</span>, end=<span style="color: #CD5555">''</span>)
|
|
<span style="color: #8B008B; font-weight: bold">else</span>:
|
|
env_list[S] = <span style="color: #CD5555">'o'</span>
|
|
interaction = <span style="color: #CD5555">''</span>.join(env_list)
|
|
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">'\r{}'</span>.format(interaction), end=<span style="color: #CD5555">''</span>)
|
|
time.sleep(FRESH_TIME)
|
|
|
|
|
|
<span style="color: #8B008B; font-weight: bold">def</span> <span style="color: #008b45">rl</span>():
|
|
<span style="color: #228B22"># main part of RL loop</span>
|
|
q_table = build_q_table(N_STATES, ACTIONS)
|
|
<span style="color: #8B008B; font-weight: bold">for</span> episode <span style="color: #8B008B">in</span> <span style="color: #658b00">range</span>(MAX_EPISODES):
|
|
step_counter = <span style="color: #B452CD">0</span>
|
|
S = <span style="color: #B452CD">0</span>
|
|
is_terminated = <span style="color: #658b00">False</span>
|
|
update_env(S, episode, step_counter)
|
|
<span style="color: #8B008B; font-weight: bold">while</span> <span style="color: #8B008B">not</span> is_terminated:
|
|
|
|
A = choose_action(S, q_table)
|
|
S_, R = get_env_feedback(S, A) <span style="color: #228B22"># take action & get next state and reward</span>
|
|
q_predict = q_table.loc[S, A]
|
|
<span style="color: #8B008B; font-weight: bold">if</span> S_ != <span style="color: #CD5555">'terminal'</span>:
|
|
q_target = R + GAMMA * q_table.iloc[S_, :].max() <span style="color: #228B22"># next state is not terminal</span>
|
|
<span style="color: #8B008B; font-weight: bold">else</span>:
|
|
q_target = R <span style="color: #228B22"># next state is terminal</span>
|
|
is_terminated = <span style="color: #658b00">True</span> <span style="color: #228B22"># terminate this episode</span>
|
|
|
|
q_table.loc[S, A] += ALPHA * (q_target - q_predict) <span style="color: #228B22"># update</span>
|
|
S = S_ <span style="color: #228B22"># move to next state</span>
|
|
|
|
update_env(S, episode, step_counter+<span style="color: #B452CD">1</span>)
|
|
step_counter += <span style="color: #B452CD">1</span>
|
|
<span style="color: #8B008B; font-weight: bold">return</span> q_table
|
|
|
|
|
|
<span style="color: #8B008B; font-weight: bold">if</span> <span style="color: #00688B">__name__</span> == <span style="color: #CD5555">"__main__"</span>:
|
|
q_table = rl()
|
|
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">'\r\nQ-table:\n'</span>)
|
|
<span style="color: #8B008B; font-weight: bold">print</span>(q_table)
|
|
</pre></div>
|
|
</section>
|
|
|
|
|
|
|
|
</div> <!-- class="slides" -->
|
|
</div> <!-- class="reveal" -->
|
|
|
|
<script src="reveal.js/lib/js/head.min.js"></script>
|
|
<script src="reveal.js/js/reveal.js"></script>
|
|
|
|
<script>
|
|
// Full list of configuration options available here:
|
|
// https://github.com/hakimel/reveal.js#configuration
|
|
Reveal.initialize({
|
|
|
|
// Display navigation controls in the bottom right corner
|
|
controls: true,
|
|
|
|
// Display progress bar (below the horiz. slider)
|
|
progress: true,
|
|
|
|
// Display the page number of the current slide
|
|
slideNumber: true,
|
|
|
|
// Push each slide change to the browser history
|
|
history: false,
|
|
|
|
// Enable keyboard shortcuts for navigation
|
|
keyboard: true,
|
|
|
|
// Enable the slide overview mode
|
|
overview: true,
|
|
|
|
// Vertical centering of slides
|
|
//center: true,
|
|
center: false,
|
|
|
|
// Enables touch navigation on devices with touch input
|
|
touch: true,
|
|
|
|
// Loop the presentation
|
|
loop: false,
|
|
|
|
// Change the presentation direction to be RTL
|
|
rtl: false,
|
|
|
|
// Turns fragments on and off globally
|
|
fragments: true,
|
|
|
|
// Flags if the presentation is running in an embedded mode,
|
|
// i.e. contained within a limited portion of the screen
|
|
embedded: false,
|
|
|
|
// Number of milliseconds between automatically proceeding to the
|
|
// next slide, disabled when set to 0, this value can be overwritten
|
|
// by using a data-autoslide attribute on your slides
|
|
autoSlide: 0,
|
|
|
|
// Stop auto-sliding after user input
|
|
autoSlideStoppable: true,
|
|
|
|
// Enable slide navigation via mouse wheel
|
|
mouseWheel: false,
|
|
|
|
// Hides the address bar on mobile devices
|
|
hideAddressBar: true,
|
|
|
|
// Opens links in an iframe preview overlay
|
|
previewLinks: false,
|
|
|
|
// Transition style
|
|
transition: 'default', // default/cube/page/concave/zoom/linear/fade/none
|
|
|
|
// Transition speed
|
|
transitionSpeed: 'default', // default/fast/slow
|
|
|
|
// Transition style for full page slide backgrounds
|
|
backgroundTransition: 'default', // default/none/slide/concave/convex/zoom
|
|
|
|
// Number of slides away from the current that are visible
|
|
viewDistance: 3,
|
|
|
|
// Parallax background image
|
|
//parallaxBackgroundImage: '', // e.g. "'https://s3.amazonaws.com/hakim-static/reveal-js/reveal-parallax-1.jpg'"
|
|
|
|
// Parallax background size
|
|
//parallaxBackgroundSize: '' // CSS syntax, e.g. "2100px 900px"
|
|
|
|
theme: Reveal.getQueryHash().theme, // available themes are in reveal.js/css/theme
|
|
transition: Reveal.getQueryHash().transition || 'default', // default/cube/page/concave/zoom/linear/none
|
|
|
|
});
|
|
|
|
Reveal.initialize({
|
|
dependencies: [
|
|
// Cross-browser shim that fully implements classList - https://github.com/eligrey/classList.js/
|
|
{ src: 'reveal.js/lib/js/classList.js', condition: function() { return !document.body.classList; } },
|
|
|
|
// Interpret Markdown in <section> elements
|
|
{ src: 'reveal.js/plugin/markdown/marked.js', condition: function() { return !!document.querySelector( '[data-markdown]' ); } },
|
|
{ src: 'reveal.js/plugin/markdown/markdown.js', condition: function() { return !!document.querySelector( '[data-markdown]' ); } },
|
|
|
|
// Syntax highlight for <code> elements
|
|
{ src: 'reveal.js/plugin/highlight/highlight.js', async: true, callback: function() { hljs.initHighlightingOnLoad(); } },
|
|
|
|
// Zoom in and out with Alt+click
|
|
{ src: 'reveal.js/plugin/zoom-js/zoom.js', async: true, condition: function() { return !!document.body.classList; } },
|
|
|
|
// Speaker notes
|
|
{ src: 'reveal.js/plugin/notes/notes.js', async: true, condition: function() { return !!document.body.classList; } },
|
|
|
|
// Remote control your reveal.js presentation using a touch device
|
|
//{ src: 'reveal.js/plugin/remotes/remotes.js', async: true, condition: function() { return !!document.body.classList; } },
|
|
|
|
// MathJax
|
|
//{ src: 'reveal.js/plugin/math/math.js', async: true }
|
|
]
|
|
});
|
|
|
|
Reveal.initialize({
|
|
|
|
// The "normal" size of the presentation, aspect ratio will be preserved
|
|
// when the presentation is scaled to fit different resolutions. Can be
|
|
// specified using percentage units.
|
|
width: 1170, // original: 960,
|
|
height: 700,
|
|
|
|
// Factor of the display size that should remain empty around the content
|
|
margin: 0.1,
|
|
|
|
// Bounds for smallest/largest possible scale to apply to content
|
|
minScale: 0.2,
|
|
maxScale: 1.0
|
|
|
|
});
|
|
</script>
|
|
|
|
<!-- begin footer logo
|
|
<div style="position: absolute; bottom: 0px; left: 0; margin-left: 0px">
|
|
<img src="somelogo.png">
|
|
</div>
|
|
end footer logo -->
|
|
|
|
|
|
|
|
</body>
|
|
</html>
|