<div dir="auto"><div>Yes, that's the basic gist. When I talked to Reid at the PI meeting last year, he expressed concern about coordination and collaboration. I think the main thing is to be able to articulate, in both reports, what UMBC is doing, what Brown is doing, and what we're collaborating on - and how that collective set of activities is providing a coherent overall project. The "collaborative project" should be more than just what we're doing, plus what you're doing. <div dir="auto"><div dir="auto"><br></div><div dir="auto">Marie</div></div><br><br><div class="gmail_quote"><div dir="ltr">On Tue, Aug 21, 2018, 5:21 PM Littman, Michael <<a href="mailto:mlittman@cs.brown.edu">mlittman@cs.brown.edu</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr">Not sure what you mean about "this collaboration issue". As far as I know, the description Dave sent is the main point of direct collaboration.<div><br></div><div>Are you saying you think that we need to find more points of contact to soothe the PM?</div></div><br><div class="gmail_quote"><div dir="ltr">On Tue, Aug 21, 2018 at 10:57 AM Marie desJardins <<a href="mailto:mariedj@umbc.edu" target="_blank" rel="noreferrer">mariedj@umbc.edu</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div text="#000000" bgcolor="#FFFFFF">
<font face="Lucida Grande">Thanks, David, this is really helpful.<br>
<br>
Michael/Stefanie, can you share your thoughts on this
collaboration issue?<br>
<br>
Marie<br>
</font><br>
<div class="m_4590941436531286551m_-6464341634061768485moz-cite-prefix">On 8/14/18 11:57 AM, Abel, David wrote:<br>
</div>
<blockquote type="cite">
<div dir="ltr">Hi all,
<div><br>
</div>
<div class="gmail_extra">
<div class="gmail_quote">
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div text="#000000" bgcolor="#FFFFFF"><font face="Lucida
Grande">I received the following comment from Reid
Simmons with a request to revise and resubmit the
annual report:<br>
<br>
"Unclear whether all the reported work was done at
UMBC or some was done at Brown. If some of the work
was done by collaborators, please indicate this; if
the work was done fully at UMBC, please indicate what
types of collaboration were done in the past year (and
what are expected in the coming year)."<br>
<br>
The submitted version is attached. Can some
combination of John, Michael, Stefanie, Nakul, and
David provide some input about collaborations? I do
know that Reid has expressed some concern in the past
about how/whether the two project sites are
coordinating, so emphasizing the ways in which our
work is coordinating and complementing each other
would be good to add.<br>
</font></div>
</blockquote>
<div><br>
</div>
<div>John and I have been collaborating on a project
together since around March. I don't see the project
described in the attached AMDP writeup, so here's a brief
description.</div>
<div><br>
</div>
<div>At a high level, we're investigating whether we can
improve how option models are computed, both in terms of
(1) learning options and their models, and (2) using
options to plan (as part of a hierarchy or on their own).
The main insight we're exploiting to improve over current
option models is that the option model shouldn't depend on
the exact number of lower level actions taken in an
execution of the option. Instead, we offer a variant of
options that retains a <i>rough estimate</i> of the
number of lower level actions taken on a per state basis.
This value is most critical in figuring out how much to
discount future plans.</div>
<div><br>
</div>
<div>So far we've shown:</div>
<div>
<ol>
<li>A sample bound for learning options using this new
model. (How many samples $(s, o, s')$ are needed to
determine <i>roughly</i> how many lower level actions
will be taken when $o$ is executed in $s$?)</li>
<li>A bound on the value function when using the new,
learned, option model, compared to using the usual
option models.</li>
<li>John has conducted some really interesting
experiments in a variety of Taxi instances that
showcase the potential of the method. In short: we can
learn faster, and with lower variance, if we use the
new option model.</li>
</ol>
<div>We have several ongoing subtasks:</div>
</div>
<div>
<ul>
<li>Use the new option model to inform the option reward
model, too.</li>
<li>Prove similar results as (1.) and (2.) above with
the new option reward model.</li>
<li>Target option models with low variance.</li>
</ul>
</div>
<div><a href="https://www.sharelatex.com/project/5ab3e0446f167e439582055a" target="_blank" rel="noreferrer">Our writeup is here</a>. Hope
this helps! Let me know if there is any other information
that would be useful --</div>
<div><br>
</div>
<div>Best,</div>
<div>-Dave</div>
<div> </div>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div text="#000000" bgcolor="#FFFFFF"><font face="Lucida
Grande"> <br>
Michael <br>
<span class="m_4590941436531286551m_-6464341634061768485HOEnZb"><font color="#888888"> <br>
</font></span></font><span class="m_4590941436531286551m_-6464341634061768485HOEnZb"><font color="#888888">
<div class="m_4590941436531286551m_-6464341634061768485m_-2649567925692750419moz-signature">--
<br>
Dr. Marie desJardins <br>
Associate Dean for Academic Affairs <br>
College of Engineering and Information Technology
<br>
University of Maryland, Baltimore County <br>
1000 Hilltop Circle <br>
Baltimore MD 21250 <br>
<br>
Email: <a class="m_4590941436531286551m_-6464341634061768485m_-2649567925692750419moz-txt-link-abbreviated" href="mailto:mariedj@umbc.edu" target="_blank" rel="noreferrer">mariedj@umbc.edu</a> <br>
Voice: 410-455-3967 <br>
Fax: 410-455-3559</div>
</font></span></div>
<br>
_______________________________________________<br>
Robot-learning mailing list<br>
<a href="mailto:Robot-learning@cs.umbc.edu" target="_blank" rel="noreferrer">Robot-learning@cs.umbc.edu</a><br>
<a href="https://lists.cs.umbc.edu/mailman/listinfo/robot-learning" rel="noreferrer noreferrer" target="_blank">https://lists.cs.umbc.edu/mailman/listinfo/robot-learning</a><br>
<br>
</blockquote>
</div>
<br>
</div>
</div>
<br>
<fieldset class="m_4590941436531286551m_-6464341634061768485mimeAttachmentHeader"></fieldset>
<br>
<pre>_______________________________________________
Robot-learning mailing list
<a class="m_4590941436531286551m_-6464341634061768485moz-txt-link-abbreviated" href="mailto:Robot-learning@cs.umbc.edu" target="_blank" rel="noreferrer">Robot-learning@cs.umbc.edu</a>
<a class="m_4590941436531286551m_-6464341634061768485moz-txt-link-freetext" href="https://lists.cs.umbc.edu/mailman/listinfo/robot-learning" target="_blank" rel="noreferrer">https://lists.cs.umbc.edu/mailman/listinfo/robot-learning</a>
</pre>
</blockquote>
<br>
</div>
_______________________________________________<br>
Robot-learning mailing list<br>
<a href="mailto:Robot-learning@cs.umbc.edu" target="_blank" rel="noreferrer">Robot-learning@cs.umbc.edu</a><br>
<a href="https://lists.cs.umbc.edu/mailman/listinfo/robot-learning" rel="noreferrer noreferrer" target="_blank">https://lists.cs.umbc.edu/mailman/listinfo/robot-learning</a><br>
</blockquote></div>
_______________________________________________<br>
Robot-learning mailing list<br>
<a href="mailto:Robot-learning@cs.umbc.edu" target="_blank" rel="noreferrer">Robot-learning@cs.umbc.edu</a><br>
<a href="https://lists.cs.umbc.edu/mailman/listinfo/robot-learning" rel="noreferrer noreferrer" target="_blank">https://lists.cs.umbc.edu/mailman/listinfo/robot-learning</a><br>
</blockquote></div></div></div>