<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=us-ascii">
</head>
<body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;" class="">
<div style="margin: 0in 0in 0.0001pt;" class=""><font face="Arial" style="font-size: 14px;" class=""><span class="">Our next Mobilize Center Seminar is scheduled for Thursday, March 9, and features
<b class="">Sergey Levine </b><span class="">from</span> the University of California, Berkeley</span><span class="">. We look forward to seeing you!</span></font></div>
<div style="margin: 0in 0in 0.0001pt;" class=""><font face="Arial" class="" style="font-size: 14px;"> <b class=""><o:p class=""></o:p></b></font></div>
<div style="margin: 0in 0in 0.0001pt;" class=""><font face="Arial" class="" style="font-size: 14px;"><b class="">TITLE:</b> <o:p class=""></o:p></font></div>
<div class="">
<div style="margin: 0in 0in 0.0001pt;" class=""><b class=""><font face="Arial" style="font-size: 14px;" class=""><span class="">Deep Reinforcement Learning in Robotics</span><span class=""> </span></font></b></div>
</div>
<div style="margin: 0in 0in 0.0001pt;" class=""><font face="Arial" class="" style="font-size: 14px;"> <o:p class=""></o:p></font></div>
<div style="margin: 0in 0in 0.0001pt;" class=""><font face="Arial" class="" style="font-size: 14px;"><b class="">WHEN:</b> <o:p class=""></o:p></font></div>
<div style="margin: 0in 0in 0.0001pt;" class=""><font face="Arial" class="" style="font-size: 14px;"><b class="">Thursday, March 9</b><o:p class=""></o:p></font></div>
<div style="margin: 0in 0in 0.0001pt;" class=""><font face="Arial" class="" style="font-size: 14px;"><b class="">noon - 1 pm</b> <o:p class=""></o:p></font></div>
<div style="margin: 0in 0in 0.0001pt;" class=""><font face="Arial" class="" style="font-size: 14px;"> <o:p class=""></o:p></font></div>
<div style="margin: 0in 0in 0.0001pt;" class=""><font face="Arial" class="" style="font-size: 14px;"><b class="">WHERE:</b> <o:p class=""></o:p></font></div>
<div style="margin: 0in 0in 0.0001pt;" class=""><font face="Arial" class="" style="font-size: 14px;"><b class=""><span style="color: rgb(251, 2, 7);" class="">Y2E2 300, Stanford University </span></b><o:p class=""></o:p></font></div>
<div style="margin: 0in 0in 0.0001pt;" class=""><font face="Arial" class="" style="font-size: 14px;"> <o:p class=""></o:p></font></div>
<div style="margin: 0in 0in 0.0001pt;" class=""><font face="Arial" class="" style="font-size: 14px;"><b class="">Abstract:</b><o:p class=""></o:p></font></div>
<div class="">
<div class="">
<div style="margin: 0in 0in 0.0001pt;" class=""><font face="Arial" style="font-size: 14px;" class="">Robotic learning has long held the promise of automating the design of complex robotic behavioral skills. However, effective deployment of robotic learning
typically hinged on the design of suitable controller representations, from splines to dynamic movement primitives. Expressive, high-capacity models such as deep neural networks have proven to be exceptionally proficient at reducing or removing the need for
manual representation design in a range of fields, from computer vision to machine translation to speech processing. Could the same kind of transformation take place in robotic learning? In this talk, I will discuss recent advances in deep reinforcement learning
that have enabled the automation of controller design for robotic hands, complex manipulation skills, and locomotion. I will discuss the tradeoffs between various reinforcement learning methods, present some recent experimental results, and discuss ongoing
challenges in this new field.</font></div>
</div>
</div>
<div style="margin: 0in 0in 0.0001pt;" class=""><font face="Arial" class="" style="font-size: 14px;"> <o:p class=""></o:p></font></div>
<div class="">
<div style="margin: 0in 0in 0.0001pt;" class=""><font face="Arial" class="" style="font-size: 14px;"><b class="">Bio:</b><o:p class=""></o:p></font></div>
</div>
<div class="">
<div style="margin: 0in 0in 0.0001pt; text-align: justify;" class=""><font face="Arial" style="font-size: 14px;" class=""><span style="text-align: start;" class="">Sergey Levine received a BS and MS in Computer Science from Stanford University in 2009, and
a Ph.D. in Computer Science from Stanford University in 2014. He joined the faculty of the Department of Electrical Engineering and Computer Sciences at UC Berkeley in fall 2016. His work focuses on machine learning for decision making and control, with an
emphasis on deep learning and reinforcement learning algorithms. Applications of his work include autonomous robots and vehicles, as well as computer vision and graphics. His research includes developing algorithms for end-to-end training of deep neural network
policies that combine perception and control, scalable algorithms for inverse reinforcement learning, deep reinforcement learning algorithms, and more.</span><br style="text-align: start;" class="">
<span class=""> </span></font></div>
</div>
<div style="margin: 0in 0in 0.0001pt;" class=""><font face="Arial" class="" style="font-size: 14px;">Please see<span style="color: rgb(43, 82, 255);" class=""> </span><a href="http://mobilize.stanford.edu/events/" style="color: rgb(149, 79, 114);" class=""><span style="color: rgb(107, 0, 109);" class="">Mobilize
Events</span></a> for a list of upcoming speakers.</font></div>
<div style="margin: 0in 0in 0.0001pt;" class=""><font face="Arial" class="" style="font-size: 14px;"><br class="">
</font></div>
<div style="margin: 0in 0in 0.0001pt;" class=""><span class="" style="font-size: 14px;"><font face="Arial" class="">Diane Bush</font></span></div>
<div class="">
<div class=""><font face="Arial" class="" style="font-size: 14px;">Assistant to Professor Scott Delp<br class="">
NMBL, Mobilize Center, OpenSim<br class="">
Stanford University<br class="">
<a href="mailto:dbush1@stanford.edu" class="">dbush1@stanford.edu</a><br class="">
</font></div>
</div>
<br class="">
</body>
</html>