<div dir="ltr">A gentle reminder that the talk is tomorrow (Tuesday) noon in NSH 1507!</div><div class="gmail_extra"><br><div class="gmail_quote">On Sat, Mar 18, 2017 at 12:00 PM,  <span dir="ltr"><<a href="mailto:ai-seminar-announce-request@cs.cmu.edu" target="_blank">ai-seminar-announce-request@cs.cmu.edu</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Send ai-seminar-announce mailing list submissions to<br>
        <a href="mailto:ai-seminar-announce@cs.cmu.edu">ai-seminar-announce@cs.cmu.edu</a><br>
<br>
To subscribe or unsubscribe via the World Wide Web, visit<br>
        <a href="https://mailman.srv.cs.cmu.edu/mailman/listinfo/ai-seminar-announce" rel="noreferrer" target="_blank">https://mailman.srv.cs.cmu.<wbr>edu/mailman/listinfo/ai-<wbr>seminar-announce</a><br>
or, via email, send a message with subject or body 'help' to<br>
        <a href="mailto:ai-seminar-announce-request@cs.cmu.edu">ai-seminar-announce-request@<wbr>cs.cmu.edu</a><br>
<br>
You can reach the person managing the list at<br>
        <a href="mailto:ai-seminar-announce-owner@cs.cmu.edu">ai-seminar-announce-owner@cs.<wbr>cmu.edu</a><br>
<br>
When replying, please edit your Subject line so it is more specific<br>
than "Re: Contents of ai-seminar-announce digest..."<br>
<br>
<br>
Today's Topics:<br>
<br>
   1.  AI Lunch -- Wen Sun -- March 21 (Unusual Room: NSH       1507)<br>
      (Adams Wei Yu)<br>
<br>
<br>
------------------------------<wbr>------------------------------<wbr>----------<br>
<br>
Message: 1<br>
Date: Fri, 17 Mar 2017 23:34:07 -0400<br>
From: Adams Wei Yu <<a href="mailto:weiyu@cs.cmu.edu">weiyu@cs.cmu.edu</a>><br>
To: <a href="mailto:ai-seminar-announce@cs.cmu.edu">ai-seminar-announce@cs.cmu.edu</a><br>
Subject: [AI Seminar] AI Lunch -- Wen Sun -- March 21 (Unusual Room:<br>
        NSH     1507)<br>
Message-ID:<br>
        <CABzq7eq+SV=<a href="mailto:czupGEGXK_XVYmeNwvRgH9WnNessGpAn9BeT1nw@mail.gmail.com">czupGEGXK_<wbr>XVYmeNwvRgH9WnNessGpAn9BeT1nw@<wbr>mail.gmail.com</a>><br>
Content-Type: text/plain; charset="utf-8"<br>
<br>
Dear faculty and students,<br>
<br>
We look forward to seeing you Next Tuesday, March 21, at noon in *NSH 1507*<br>
for AI lunch. To learn more about the seminar and lunch, please visit the AI<br>
 Lunch webpage <<a href="http://www.cs.cmu.edu/~aiseminar/" rel="noreferrer" target="_blank">http://www.cs.cmu.edu/~<wbr>aiseminar/</a>>.<br>
<br>
On Tuesday, Wen Sun <<a href="http://www.cs.cmu.edu/~wensun/" rel="noreferrer" target="_blank">http://www.cs.cmu.edu/~<wbr>wensun/</a>> will give a talk<br>
titled *Differentiable Imitation Learning and Sequential Prediction*.<br>
<br>
*Abstract*: Recently, researchers have demonstrated state-of-the-art<br>
performance on sequential decision making problems (e.g., robotics control,<br>
sequential prediction) with deep neural networks and Reinforcement Learning<br>
(RL). However, for some of these problems, oracles that can demonstrate<br>
good performance are available during training. In this work, we propose<br>
AggreVaTeD, a policy gradient extension of the Imitation Learning (IL)<br>
approach of Ross & Bagnell (2014) that can leverage oracles to achieve<br>
faster and more accurate solutions with less training data than with a<br>
less-informed RL approaches. Specifically, we provide a comprehensive<br>
theoretical study of IL that demonstrates we can expect up to exponentially<br>
lower sample complexity for learning with AggreVaTeD than with RL<br>
algorithms. Finally, we present two stochastic gradient procedures that<br>
learn neural network policies for several problems including a sequential<br>
prediction task as well as various high dimensional robotics control<br>
problems. Our results and theory indicate that the proposed approach can<br>
achieve superior performance with respect to the oracle when the<br>
demonstrator is sub-optimal.<br>
<br>
This a joint work with Arun Venkatraman, Geoff Gordon, Byron Boots and Drew<br>
Bagnell.<br>
-------------- next part --------------<br>
An HTML attachment was scrubbed...<br>
URL: <<a href="http://mailman.srv.cs.cmu.edu/pipermail/ai-seminar-announce/attachments/20170317/371f8226/attachment-0001.html" rel="noreferrer" target="_blank">http://mailman.srv.cs.cmu.<wbr>edu/pipermail/ai-seminar-<wbr>announce/attachments/20170317/<wbr>371f8226/attachment-0001.html</a>><br>
<br>
------------------------------<br>
<br>
Subject: Digest Footer<br>
<br>
______________________________<wbr>_________________<br>
ai-seminar-announce mailing list<br>
<a href="mailto:ai-seminar-announce@cs.cmu.edu">ai-seminar-announce@cs.cmu.edu</a><br>
<a href="https://mailman.srv.cs.cmu.edu/mailman/listinfo/ai-seminar-announce" rel="noreferrer" target="_blank">https://mailman.srv.cs.cmu.<wbr>edu/mailman/listinfo/ai-<wbr>seminar-announce</a><br>
<br>
------------------------------<br>
<br>
End of ai-seminar-announce Digest, Vol 72, Issue 6<br>
******************************<wbr>********************<br>
</blockquote></div><br></div>