<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
</head>
<body text="#000000" bgcolor="#FFFFFF">
<p><br>
</p>
<div class="moz-forward-container"><br>
<br>
-------- Forwarded Message --------
<table class="moz-email-headers-table" cellspacing="0"
cellpadding="0" border="0">
<tbody>
<tr>
<th valign="BASELINE" nowrap="nowrap" align="RIGHT">Subject:
</th>
<td>Fwd: This Weeks CCDC Seminar: "Deep Learning to Learn"
by Pieter Abbeel</td>
</tr>
<tr>
<th valign="BASELINE" nowrap="nowrap" align="RIGHT">Date: </th>
<td>Fri, 26 Apr 2019 10:02:11 -0700</td>
</tr>
<tr>
<th valign="BASELINE" nowrap="nowrap" align="RIGHT">From: </th>
<td>Yon Visell <a class="moz-txt-link-rfc2396E" href="mailto:yonvisell@ece.ucsb.edu"><yonvisell@ece.ucsb.edu></a></td>
</tr>
<tr>
<th valign="BASELINE" nowrap="nowrap" align="RIGHT">To: </th>
<td>Students list <a class="moz-txt-link-rfc2396E" href="mailto:students@mat.ucsb.edu"><students@mat.ucsb.edu></a>,
<a class="moz-txt-link-abbreviated" href="mailto:core-faculty@mat.ucsb.edu">core-faculty@mat.ucsb.edu</a></td>
</tr>
</tbody>
</table>
<br>
<br>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
Some of you may be interested in this seminar today at 3pm in Webb
1100
<div class=""><br class="">
</div>
<div class="">Best,</div>
<div class="">Yon</div>
<div class=""><br class="">
<div><br class="">
<blockquote type="cite" class="">
<div class="">Begin forwarded message:</div>
<br class="Apple-interchange-newline">
<div style="margin-top: 0px; margin-right: 0px;
margin-bottom: 0px; margin-left: 0px;" class=""><span
style="font-family: -webkit-system-font, Helvetica Neue,
Helvetica, sans-serif; color:rgba(0, 0, 0, 1.0);"
class=""><b class="">From: </b></span><span
style="font-family: -webkit-system-font, Helvetica Neue,
Helvetica, sans-serif;" class="">ccdc-admin <<a
href="mailto:ccdc-admin@ece.ucsb.edu" class=""
moz-do-not-send="true">ccdc-admin@ece.ucsb.edu</a>><br
class="">
</span></div>
<div style="margin-top: 0px; margin-right: 0px;
margin-bottom: 0px; margin-left: 0px;" class=""><span
style="font-family: -webkit-system-font, Helvetica Neue,
Helvetica, sans-serif; color:rgba(0, 0, 0, 1.0);"
class=""><b class="">Subject: </b></span><span
style="font-family: -webkit-system-font, Helvetica Neue,
Helvetica, sans-serif;" class=""><b class="">This Weeks
CCDC Seminar: "Deep Learning to Learn" by Pieter
Abbeel</b><br class="">
</span></div>
<div style="margin-top: 0px; margin-right: 0px;
margin-bottom: 0px; margin-left: 0px;" class=""><span
style="font-family: -webkit-system-font, Helvetica Neue,
Helvetica, sans-serif; color:rgba(0, 0, 0, 1.0);"
class=""><b class="">Date: </b></span><span
style="font-family: -webkit-system-font, Helvetica Neue,
Helvetica, sans-serif;" class="">April 23, 2019 at
3:31:14 PM PDT<br class="">
</span></div>
<div style="margin-top: 0px; margin-right: 0px;
margin-bottom: 0px; margin-left: 0px;" class=""><span
style="font-family: -webkit-system-font, Helvetica Neue,
Helvetica, sans-serif; color:rgba(0, 0, 0, 1.0);"
class=""><b class="">To: </b></span><span
style="font-family: -webkit-system-font, Helvetica Neue,
Helvetica, sans-serif;" class=""><a
href="mailto:ccdc-students@ece.ucsb.edu" class=""
moz-do-not-send="true">ccdc-students@ece.ucsb.edu</a>,
<a href="mailto:ccdc-faculty@ece.ucsb.edu" class=""
moz-do-not-send="true">ccdc-faculty@ece.ucsb.edu</a><br
class="">
</span></div>
<br class="">
<div class="">
<div dir="ltr" style="caret-color: rgb(0, 0, 0);
font-family: Helvetica; font-size: 12px; font-style:
normal; font-variant-caps: normal; font-weight: normal;
letter-spacing: normal; text-align: start; text-indent:
0px; text-transform: none; white-space: normal;
word-spacing: 0px; -webkit-text-stroke-width: 0px;
text-decoration: none;" class="">
<div dir="ltr" class="">
<div dir="ltr" class="">
<div dir="ltr" class="">
<div dir="ltr" class="">
<div dir="ltr" class="">
<div class="gmail_default" style="font-family:
tahoma, sans-serif;">
<div class="gmail_quote" style="font-family:
Arial, Helvetica, sans-serif;">
<div dir="ltr" class="">
<div dir="ltr" class="">
<div dir="ltr" class="">
<div dir="ltr" class="">
<div dir="ltr" class="">
<div class="gmail_default"
style="font-family: tahoma,
sans-serif;">
<div dir="ltr"
style="font-family: Arial,
Helvetica, sans-serif;"
class="">
<div dir="ltr" class="">
<div dir="ltr" class="">
<div dir="ltr" class="">
<div dir="ltr"
class="">
<div dir="ltr"
class="">
<div
class="gmail_default">
<div
class="gmail_quote">
<div dir="ltr"
class="">
<div dir="ltr"
class="">
<div
class="gmail_default">
<div class="">
<div
style="margin:
0in 0in
0.0001pt;"
class=""><b
class=""><font
class=""
size="4"><span
style="color:
rgb(34, 34,
34);" class="">Deep
Learning to
Learn</span><span
style="font-family: Calibri, sans-serif; color: rgb(34, 34, 34);"
class=""> </span></font></b><span
style="font-family: -webkit-standard; font-size: inherit;" class=""></span><br
class="">
</div>
<div
style="font-size:
small; margin:
0in 0in
0.0001pt;"
class=""><span
style="font-family: arial, helvetica, sans-serif; color: rgb(34, 34,
34);" class=""><br
class="">
</span></div>
<div
style="font-size:
small; margin:
0in 0in
0.0001pt;"
class=""><span
style="font-family: arial, helvetica, sans-serif; color: rgb(34, 34,
34);" class="">By </span><span
class="gmail_default" style="font-family: arial, helvetica, sans-serif;
color: rgb(34,
34, 34);">Pieter
Abbeel</span></div>
<div
style="font-size:
small; margin:
0in 0in
0.0001pt;"
class=""><span
style="font-family: arial, helvetica, sans-serif; color: rgb(34, 34,
34);" class="">Friday,
April 26th</span><span
style="font-family: arial, helvetica, sans-serif; color: rgb(34, 34,
34);" class=""> </span><font
style="font-family: arial, helvetica, sans-serif; color: rgb(34, 34,
34);" class=""
size="2">@ 3pm
in Webb 1100</font></div>
<div
style="font-size:
small; margin:
0in 0in
0.0001pt;"
class=""><font
style="font-family: arial, helvetica, sans-serif; color: rgb(34, 34,
34);
text-align:
justify;"
class=""><b
class=""><br
class="">
</b></font></div>
<div
style="font-size:
small; margin:
0in 0in
0.0001pt;"
class=""><font
style="font-family: arial, helvetica, sans-serif; color: rgb(34, 34,
34);
text-align:
justify;"
class=""><b
class="">Abstract</b>: </font><span
style="color:
rgb(34, 34,
34);" class="">Reinforcement
learning and
imitation
learning have
seen success
in many
domains,
including
autonomous
helicopter
flight, Atari,
simulated
locomotion,
Go, robotic
manipulation.
However, the
amount of data
required for
these methods
remains very
high. In
contrast,
humans can
pick up new
skills far
more quickly.
To do so,
humans might
rely on a
better
learning
algorithm or
on a better
prior
(potentially
learned from
past
experience),
and likely on
both. In this
talk I will
describe some
recent work on
meta-learning
for action,
where agents
learn the
imitation/reinforcement
learning
algorithms and
learn the
prior. This
has enabled
acquiring new
skills from
just a single
demonstration
or just a few
trials. While
originally
designed for
imitation and
RL, our work
is more
generally
applicable and
also advanced
the state of
the art in
image
recognition
from a small
number of
examples.</span></div>
<p
class="MsoNormal"
style="font-size: small; margin: 0in 0in 0.0001pt; font-family: Calibri,
sans-serif;"><span
style="color:
rgb(34, 34,
34);" class=""></span></p>
<div
style="font-size:
small; margin:
0in 0in
0.0001pt;"
class=""><b
style="text-align:
justify;
color: rgb(34,
34, 34);
font-family:
arial,
helvetica,
sans-serif;"
class=""><br
class="">
</b></div>
<div
style="font-size:
small; margin:
0in 0in
0.0001pt;"
class=""><b
style="text-align:
justify;
color: rgb(34,
34, 34);
font-family:
arial,
helvetica,
sans-serif;"
class="">Bio: </b>Pieter
Abbeel is
Professor and
Director of
the Robot
Learning Lab
at UC Berkeley
[2008- ],
Co-Founder of<span
class="Apple-converted-space"> </span><a href="http://covariant.ai/"
class=""
moz-do-not-send="true">covariant.ai</a><span
class="Apple-converted-space"> </span>[2017- ], Co-Founder of Gradescope
[2014- ],
Advisor to
OpenAI,
Founding
Faculty
Partner
AI@TheHouse,
Advisor to
many
AI/Robotics
start-ups. He
works in
machine
learning and
robotics. In
particular his
research
focuses on
making robots
learn from
people
(apprenticeship
learning), how
to make robots
learn through
their own
trial and
error
(reinforcement
learning), and
how to speed
up skill
acquisition
through
learning-to-learn
(meta-learning). His robots have learned advanced helicopter
aerobatics,
knot-tying,
basic
assembly,
organizing
laundry,
locomotion,
and
vision-based
robotic
manipulation.
He has won
numerous
awards,
including best
paper awards
at ICML, NIPS
and ICRA,
early career
awards from
NSF, Darpa,
ONR, AFOSR,
Sloan, TR35,
IEEE, and the
Presidential
Early Career
Award for
Scientists and
Engineers
(PECASE). </div>
<div
style="margin:
0in 0in
0.0001pt;"
class="">Pieter's
work is
frequently
featured in
the popular
press,
including New
York Times,
BBC,
Bloomberg,
Wall Street
Journal,
Wired, Forbes,
Tech Review,
NPR, Rolling
Stone. (<a
href="http://www.cs.berkeley.edu/~pabbeel"
class=""
moz-do-not-send="true">www.cs.berkeley.edu/~pabbeel</a>)</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
<div class=""><br class="">
</div>
--<span class="Apple-converted-space"> </span><br
class="">
<div dir="ltr" class="gmail_signature">
<div dir="ltr" class="">
<div class="">
<div dir="ltr" class="">
<div class="">
<div dir="ltr" class="">
<div class="">
<div dir="ltr" class="">
<div dir="ltr" class="">
<div dir="ltr" class="">
<div class="">
<div dir="ltr" class=""><font
class="" size="2"
face="monospace,
monospace">S</font><span
style="font-family:
monospace,
monospace;" class="">tephanie
Löfgren</span></div>
</div>
<div class="">
<div dir="ltr" class="">
<div
style="text-align:
left;" class=""><font
class="" size="2"><span
style="font-family: monospace, monospace;" class="">Administrative
Coordinator</span></font></div>
</div>
</div>
<div class="">
<div dir="ltr" class="">
<div class=""><font
class="" size="2"><span
style="font-family: monospace, monospace;" class="">Center for Control,
Dynamical-systems and Computation</span><br class="">
</font></div>
<div class=""><font
class="" size="2"><span
style="font-family: monospace, monospace;" class="">5119 Harold Frank
Hall</span><br
class="">
</font></div>
<div class=""><font
class="" size="2"><span
style="font-family: monospace, monospace;" class="">University of
California,
Santa Barbara</span><br
class="">
</font></div>
<div class=""><span
style="font-family:
monospace,
monospace;"
class=""><font
class=""
size="2">805-893-7066</font></span></div>
<div class=""><span
style="font-family:
monospace,
monospace;"
class=""><font
class=""
size="2"><br
class="">
</font></span></div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</blockquote>
</div>
</div>
</div>
<pre class="moz-signature" cols="72">--
Tobias Hollerer
Professor, Department of Computer Science
University of California, Santa Barbara, CA 93106-5110
<a class="moz-txt-link-abbreviated" href="mailto:holl@cs.ucsb.edu">holl@cs.ucsb.edu</a>, Office: (805)284-9395, Fax: (805)893-8553 </pre>
</body>
</html>