<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body text="#000000" bgcolor="#FFFFFF">
<font face="Lucida Grande">Fri 2/2 would be good for a phone call
with Stefanie and Michael. (Does that work for both of you? -- if
so, what time is good? I'm fairly unconstrained.)<br>
<br>
Fri 2/2 won't work for a larger group meeting, though -- John will
be at AAAI. I'll be traveling on Fri 2/9 but John should be back
by then, so maybe we could plan a joint group meeting that day --
do you still have your regular meetings on Fridays?<br>
<br>
Marie<br>
<br>
</font><br>
<div class="moz-cite-prefix">On 1/21/18 11:23 AM, Stefanie Tellex
wrote:<br>
</div>
<blockquote type="cite"
cite="mid:05615ee0-d5c1-5a22-f499-4aa211d1db90@cs.brown.edu">I
agree, for after the winter deadlines.
<br>
<br>
Stefanie
<br>
<br>
On 01/21/2018 04:51 AM, Lawson Wong wrote:
<br>
<blockquote type="cite">So have <a class="moz-txt-link-abbreviated" href="mailto:kcaluru@brown.edu">kcaluru@brown.edu</a>
<a class="moz-txt-link-rfc2396E" href="mailto:kcaluru@brown.edu"><mailto:kcaluru@brown.edu></a> and <a class="moz-txt-link-abbreviated" href="mailto:miles_holland@brown.edu">miles_holland@brown.edu</a>
<a class="moz-txt-link-rfc2396E" href="mailto:miles_holland@brown.edu"><mailto:miles_holland@brown.edu></a>
<br>
<br>
The reviews look like typical planning-community reviews --
generally sensible requests but clearly impossible to accomplish
within the page limit. I guess it's generally hard to please
planning reviewers unless there are some theoretical results.
Review 2 actually reads a little like one that Nakul got for his
paper...
<br>
<br>
I don't know if Michael and Stefanie have answered separately
regarding a meeting; it certainly sounds helpful to continue
discussing (AMDP) hierarchy learning. Both the IJCAI and RSS
deadlines are on that week (1/31 and 2/1 respectively), so if
possible it may be best to meet after those deadlines, such as
on Fri 2/2 -- unless the intent was to discuss before the IJCAI
deadline.
<br>
<br>
-Lawson
<br>
<br>
<br>
On Sat, Jan 20, 2018 at 6:04 AM, Littman, Michael
<<a class="moz-txt-link-abbreviated" href="mailto:mlittman@cs.brown.edu">mlittman@cs.brown.edu</a>
<a class="moz-txt-link-rfc2396E" href="mailto:mlittman@cs.brown.edu"><mailto:mlittman@cs.brown.edu></a>> wrote:
<br>
<br>
<a class="moz-txt-link-abbreviated" href="mailto:christopher_grimm@brown.edu">christopher_grimm@brown.edu</a>
<a class="moz-txt-link-rfc2396E" href="mailto:christopher_grimm@brown.edu"><mailto:christopher_grimm@brown.edu></a> has
<br>
graduated.
<br>
<br>
<br>
On Fri, Jan 19, 2018 at 12:06 PM, Marie desJardins
<br>
<<a class="moz-txt-link-abbreviated" href="mailto:mariedj@cs.umbc.edu">mariedj@cs.umbc.edu</a>
<a class="moz-txt-link-rfc2396E" href="mailto:mariedj@cs.umbc.edu"><mailto:mariedj@cs.umbc.edu></a>> wrote:
<br>
<br>
Hi everyone,
<br>
<br>
I wanted to share the initial reviews we received on our
ICAPS
<br>
submission (which I've also attached). Based on the
reviews, I
<br>
think the paper is unlikely to be accepted, so we are
working to
<br>
see whether we can get some new results for an IJCAI
submission.
<br>
We are making good progress on developing hierarchical
learning
<br>
methods for AMDPs but we need to (a) move to larger/more
complex
<br>
domains, (b) develop some theoretical analysis
(complexity,
<br>
correctness, convergence), and (c) work on more
AMDP-specific
<br>
hierarchy learning techniques (right now we are using an
<br>
off-the-shelf method called HierGen that works well but
may not
<br>
necessarily find the best hierarchy for an AMDP
representation).
<br>
<br>
I'd be very interested to talk more about how this
relates to
<br>
the work that's happening at Brown, and to hear any
<br>
feedback/ideas you might have about this work.
<br>
<br>
Michael/Stephanie, could we maybe set up a time for the
three of
<br>
us to have a teleconference? I'll be on vacation next
week but
<br>
the week after that would be good. Possible times for
me -- Mon
<br>
1/29 before 11:30am, between 1-2, or after 4pm; Wed 1/31
before
<br>
10am or after 2pm; Thu 2/1 between 11-1:30 or 3-4; Fri
2/2 any time.
<br>
<br>
BTW, these are the Brown students who are on this list.
Please
<br>
let me know if anyone should be added or removed.
<br>
<br>
<a class="moz-txt-link-abbreviated" href="mailto:carl_trimbach@brown.edu">carl_trimbach@brown.edu</a>
<a class="moz-txt-link-rfc2396E" href="mailto:carl_trimbach@brown.edu"><mailto:carl_trimbach@brown.edu></a>
<br>
<a class="moz-txt-link-abbreviated" href="mailto:christopher_grimm@brown.edu">christopher_grimm@brown.edu</a>
<a class="moz-txt-link-rfc2396E" href="mailto:christopher_grimm@brown.edu"><mailto:christopher_grimm@brown.edu></a>
<br>
<a class="moz-txt-link-abbreviated" href="mailto:david_abel@brown.edu">david_abel@brown.edu</a> <a class="moz-txt-link-rfc2396E" href="mailto:david_abel@brown.edu"><mailto:david_abel@brown.edu></a>
<br>
<a class="moz-txt-link-abbreviated" href="mailto:dilip.arumugam@gmail.com">dilip.arumugam@gmail.com</a>
<a class="moz-txt-link-rfc2396E" href="mailto:dilip.arumugam@gmail.com"><mailto:dilip.arumugam@gmail.com></a>
<br>
<a class="moz-txt-link-abbreviated" href="mailto:edward_c_williams@brown.edu">edward_c_williams@brown.edu</a>
<a class="moz-txt-link-rfc2396E" href="mailto:edward_c_williams@brown.edu"><mailto:edward_c_williams@brown.edu></a>
<br>
<a class="moz-txt-link-abbreviated" href="mailto:jun_ki_lee@brown.edu">jun_ki_lee@brown.edu</a> <a class="moz-txt-link-rfc2396E" href="mailto:jun_ki_lee@brown.edu"><mailto:jun_ki_lee@brown.edu></a>
<br>
<a class="moz-txt-link-abbreviated" href="mailto:kcaluru@brown.edu">kcaluru@brown.edu</a> <a class="moz-txt-link-rfc2396E" href="mailto:kcaluru@brown.edu"><mailto:kcaluru@brown.edu></a>
<br>
<a class="moz-txt-link-abbreviated" href="mailto:lsw@brown.edu">lsw@brown.edu</a> <a class="moz-txt-link-rfc2396E" href="mailto:lsw@brown.edu"><mailto:lsw@brown.edu></a>
<br>
<a class="moz-txt-link-abbreviated" href="mailto:lucas_lehnert@brown.edu">lucas_lehnert@brown.edu</a>
<a class="moz-txt-link-rfc2396E" href="mailto:lucas_lehnert@brown.edu"><mailto:lucas_lehnert@brown.edu></a>
<br>
<a class="moz-txt-link-abbreviated" href="mailto:melrose_roderick@brown.edu">melrose_roderick@brown.edu</a>
<a class="moz-txt-link-rfc2396E" href="mailto:melrose_roderick@brown.edu"><mailto:melrose_roderick@brown.edu></a>
<br>
<a class="moz-txt-link-abbreviated" href="mailto:miles_holland@brown.edu">miles_holland@brown.edu</a>
<a class="moz-txt-link-rfc2396E" href="mailto:miles_holland@brown.edu"><mailto:miles_holland@brown.edu></a>
<br>
<a class="moz-txt-link-abbreviated" href="mailto:nakul_gopalan@brown.edu">nakul_gopalan@brown.edu</a>
<a class="moz-txt-link-rfc2396E" href="mailto:nakul_gopalan@brown.edu"><mailto:nakul_gopalan@brown.edu></a>
<br>
<a class="moz-txt-link-abbreviated" href="mailto:oberlin@cs.brown.edu">oberlin@cs.brown.edu</a> <a class="moz-txt-link-rfc2396E" href="mailto:oberlin@cs.brown.edu"><mailto:oberlin@cs.brown.edu></a>
<br>
<a class="moz-txt-link-abbreviated" href="mailto:sam_saarinen@brown.edu">sam_saarinen@brown.edu</a>
<a class="moz-txt-link-rfc2396E" href="mailto:sam_saarinen@brown.edu"><mailto:sam_saarinen@brown.edu></a>
<br>
<a class="moz-txt-link-abbreviated" href="mailto:siddharth_karamcheti@brown.edu">siddharth_karamcheti@brown.edu</a>
<br>
<a class="moz-txt-link-rfc2396E" href="mailto:siddharth_karamcheti@brown.edu"><mailto:siddharth_karamcheti@brown.edu></a>
<br>
<br>
Marie
<br>
<br>
<br>
-------- Forwarded Message --------
<br>
Subject: ICAPS 2018 review response (submission
[*NUMBER*])
<br>
Date: Thu, 11 Jan 2018 14:59:19 +0100
<br>
From: ICAPS 2018 <a class="moz-txt-link-rfc2396E" href="mailto:icaps2018@easychair.org"><icaps2018@easychair.org></a>
<br>
<a class="moz-txt-link-rfc2396E" href="mailto:icaps2018@easychair.org"><mailto:icaps2018@easychair.org></a>
<br>
To: Marie desJardins <a class="moz-txt-link-rfc2396E" href="mailto:mariedj@umbc.edu"><mariedj@umbc.edu></a>
<a class="moz-txt-link-rfc2396E" href="mailto:mariedj@umbc.edu"><mailto:mariedj@umbc.edu></a>
<br>
<br>
<br>
<br>
Dear Marie,
<br>
<br>
Thank you for your submission to ICAPS 2018. The ICAPS
2018 review
<br>
response period starts now and ends at January 13.
<br>
<br>
During this time, you will have access to the current
state of your
<br>
reviews and have the opportunity to submit a response.
Please keep in
<br>
mind the following during this process:
<br>
<br>
* Most papers have a so-called placeholder review, which
was
<br>
necessary to give the discussion leaders access to
the reviewer
<br>
discussion. Some of these reviews list questions that
already came
<br>
up during the discussion and which you may address in
your response but
<br>
in all cases the (usually enthusiastic) scores are
meaningless and you
<br>
should ignore them. Placeholder reviews are clearly
indicated as such in
<br>
the review.
<br>
<br>
* Almost all papers have three reviews. Some may have
four. A very
<br>
low number of papers are missing one review. We hope
to get that
<br>
review completed in the next day. We apologize for
this.
<br>
<br>
* The deadline for entering a response is January 13th
(at 11:59pm
<br>
UTC-12 i.e. anywhere in the world).
<br>
<br>
* Responses must be submitted through EasyChair.
<br>
<br>
* Responses are limited to 1000 words in total. You can
only enter
<br>
one response, not one per review.
<br>
<br>
* You will not be able to change your response after it
is submitted.
<br>
<br>
* The response must focus on any factual errors in the
reviews and any
<br>
questions posed by the reviewers. Try to be as
concise and as to the
<br>
point as possible.
<br>
<br>
* The review response period is an opportunity to react
to the
<br>
reviews, but not a requirement to do so. Thus, if you
feel the reviews
<br>
are accurate and the reviewers have not asked any
questions, then you
<br>
do not have to respond.
<br>
<br>
* The reviews are as submitted by the PC members,
without much
<br>
coordination between them. Thus, there may be
inconsistencies.
<br>
Furthermore, these are not the final versions of the
reviews. The
<br>
reviews can later be updated to take into account the
discussions at
<br>
the program committee meeting, and we may find it
necessary to solicit
<br>
other outside reviews after the review response
period.
<br>
<br>
* The program committee will read your responses
carefully and
<br>
take this information into account during the
discussions. On the
<br>
other hand, the program committee may not directly
respond to your
<br>
responses in the final versions of the reviews.
<br>
<br>
The reviews on your paper are attached to this letter.
To submit your
<br>
response you should log on the EasyChair Web page for
ICAPS 2018 and
<br>
select your submission on the menu.
<br>
<br>
----------------------- REVIEW 1 ---------------------
<br>
PAPER: 46
<br>
TITLE: Learning Abstracted Models and Hierarchies of
Markov Decision Processes
<br>
AUTHORS: Matthew Landen, John Winder, Shawn Squire,
Stephanie Milani, Shane Parr and Marie desJardins
<br>
<br>
Significance: 2 (modest contribution or average impact)
<br>
Soundness: 3 (correct)
<br>
Scholarship: 3 (excellent coverage of related work)
<br>
Clarity: 3 (well written)
<br>
Reproducibility: 3 (authors describe the implementation
and domains in sufficient detail)
<br>
Overall evaluation: 1 (weak accept)
<br>
Reviewer's confidence: 2 (medium)
<br>
Suitable for a demo?: 1 (no)
<br>
Nominate for Best Paper Award: 1 (no)
<br>
Nominate for Best Student Paper Award (if eligible): 1
(no)
<br>
[Applications track ONLY]: Importance and novelty of the
application: 6 (N/A (not an Applications track paper))
<br>
[Applications track ONLY]: Importance of
planning/scheduling technology to the solution of the problem: 5
(N/A (not an Applications track paper))
<br>
[Applications track ONLY] Maturity: 7 (N/A (not an
Applications track paper))
<br>
[Robotics track ONLY]: Balance of Robotics and Automated
Planning and Scheduling: 6 (N/A (not a Robotics track paper))
<br>
[Robotics Track ONLY]: Evaluation on physical
platforms/simulators: 6 (N/A (not a Robotics track paper))
<br>
[Robotics Track ONLY]: Significance of the contribution:
6 (N/A (not a Robotics track paper))
<br>
<br>
----------- Review -----------
<br>
The paper proposes a method for learning abstract Markov
decision processes (AMDP) from demonstration trajectories and
model based reinforcement learning. Experiments show that the
method is more effective than the baseline.
<br>
<br>
On the positive side, a complete method for learning
AMDP is given and is shown to be work on the problems used in
the experiments. The proposed model based reinforcement learning
method based on R-MAX is also shown to outperform the baseline
R-MAXQ.
<br>
<br>
On the negative side, the method for learning the
hierarchy, HierGen, is taken from a prior work, leaving the
adaptation of R-MAX to learn with hierarchy as the main
algorithmic novelty. No convergence proof for the earning method
is provided, although it is empirically shown to outperform the
baseline R-MAXQ. The experiments are done on toy problems,
indicating that the method is probably not ready for more
demanding practical problems.
<br>
<br>
Overall, I am inclined to vote weak accept. The problem
is difficult, so I think that the work does represent progress,
although it is not yet compelling.
<br>
<br>
----------------------- REVIEW 2 ---------------------
<br>
PAPER: 46
<br>
TITLE: Learning Abstracted Models and Hierarchies of
Markov Decision Processes
<br>
AUTHORS: Matthew Landen, John Winder, Shawn Squire,
Stephanie Milani, Shane Parr and Marie desJardins
<br>
<br>
Significance: 2 (modest contribution or average impact)
<br>
Soundness: 3 (correct)
<br>
Scholarship: 2 (relevant literature cited but could be
expanded)
<br>
Clarity: 3 (well written)
<br>
Reproducibility: 3 (authors describe the implementation
and domains in sufficient detail)
<br>
Overall evaluation: -1 (weak reject)
<br>
Reviewer's confidence: 4 (expert)
<br>
Suitable for a demo?: 2 (maybe)
<br>
Nominate for Best Paper Award: 1 (no)
<br>
Nominate for Best Student Paper Award (if eligible): 1
(no)
<br>
[Applications track ONLY]: Importance and novelty of the
application: 6 (N/A (not an Applications track paper))
<br>
[Applications track ONLY]: Importance of
planning/scheduling technology to the solution of the problem: 5
(N/A (not an Applications track paper))
<br>
[Applications track ONLY] Maturity: 7 (N/A (not an
Applications track paper))
<br>
[Robotics track ONLY]: Balance of Robotics and Automated
Planning and Scheduling: 6 (N/A (not a Robotics track paper))
<br>
[Robotics Track ONLY]: Evaluation on physical
platforms/simulators: 6 (N/A (not a Robotics track paper))
<br>
[Robotics Track ONLY]: Significance of the contribution:
6 (N/A (not a Robotics track paper))
<br>
<br>
----------- Review -----------
<br>
The authors introduce a reinforcement learning algorithm
for AMDPs that learns a hierarchical structure and a set of
hierarchical models. To learn the hierarchical structure, they
rely on an existing algorithm called HierGen. This algorithm
extracts causal structure from a set of expert trajectories in a
factored state environment.
<br>
<br>
While R-AMDP outperforms R-MAXQ on the two toy problems,
I think there is a lot more work to do to show that R-AMDP is a
good basis for developing more general algorithms. First, it
would be nice to examine the computational complexity of R-AMDP
(rather than just empirical comparison in Figure 3). Second,
what if R-AMDP is just getting lucky in the two toy tasks
presented. Maybe there are other problems where R-AMDP performs
poorly. Further, stopping the plots at 50 or 60 trials may just
be misleading since R-AMDP could be converging to a suboptimal
but pretty good policy early on. It’s also not clear that R-AMDP
can be scaled to huge state or action spaces. Does the
hierarchical structure discovered by HierGen lend itself to
transfer when the dynamics change? It would be nice to have a
more rigorous analysis of R-AMDP and a longer discussion of its
potential pitfalls (when should we expected it to succeed and
when should it fail?). There is a hind of this in the discussio!
<br>
n about HierGen’s inability to distinguish between
correlation and causation.
<br>
<br>
While reading the abstract I expected the contribution
to be in learning the hierarchy. The authors should probably
change the abstract to avoid this confusion.
<br>
<br>
----------------------- REVIEW 3 ---------------------
<br>
PAPER: 46
<br>
TITLE: Learning Abstracted Models and Hierarchies of
Markov Decision Processes
<br>
AUTHORS: Matthew Landen, John Winder, Shawn Squire,
Stephanie Milani, Shane Parr and Marie desJardins
<br>
<br>
Significance: 3 (substantial contribution or strong
impact)
<br>
Soundness: 3 (correct)
<br>
Scholarship: 3 (excellent coverage of related work)
<br>
Clarity: 3 (well written)
<br>
Reproducibility: 5 (code and domains (whichever apply)
are already publicly available)
<br>
Overall evaluation: 3 (strong accept)
<br>
Reviewer's confidence: 4 (expert)
<br>
Suitable for a demo?: 3 (yes)
<br>
Nominate for Best Paper Award: 1 (no)
<br>
Nominate for Best Student Paper Award (if eligible): 1
(no)
<br>
[Applications track ONLY]: Importance and novelty of the
application: 6 (N/A (not an Applications track paper))
<br>
[Applications track ONLY]: Importance of
planning/scheduling technology to the solution of the problem: 5
(N/A (not an Applications track paper))
<br>
[Applications track ONLY] Maturity: 7 (N/A (not an
Applications track paper))
<br>
[Robotics track ONLY]: Balance of Robotics and Automated
Planning and Scheduling: 6 (N/A (not a Robotics track paper))
<br>
[Robotics Track ONLY]: Evaluation on physical
platforms/simulators: 6 (N/A (not a Robotics track paper))
<br>
[Robotics Track ONLY]: Significance of the contribution:
6 (N/A (not a Robotics track paper))
<br>
<br>
----------- Review -----------
<br>
This is only a placeholder review. Please ignore it.
<br>
<br>
----------------------- REVIEW 4 ---------------------
<br>
PAPER: 46
<br>
TITLE: Learning Abstracted Models and Hierarchies of
Markov Decision Processes
<br>
AUTHORS: Matthew Landen, John Winder, Shawn Squire,
Stephanie Milani, Shane Parr and Marie desJardins
<br>
<br>
Significance: 2 (modest contribution or average impact)
<br>
Soundness: 2 (minor inconsistencies or small fixable
errors)
<br>
Scholarship: 3 (excellent coverage of related work)
<br>
Clarity: 1 (hard to follow)
<br>
Reproducibility: 2 (some details missing but still
appears to be replicable with some effort)
<br>
Overall evaluation: -1 (weak reject)
<br>
Reviewer's confidence: 3 (high)
<br>
Suitable for a demo?: 2 (maybe)
<br>
Nominate for Best Paper Award: 1 (no)
<br>
Nominate for Best Student Paper Award (if eligible): 1
(no)
<br>
[Applications track ONLY]: Importance and novelty of the
application: 6 (N/A (not an Applications track paper))
<br>
[Applications track ONLY]: Importance of
planning/scheduling technology to the solution of the problem: 5
(N/A (not an Applications track paper))
<br>
[Applications track ONLY] Maturity: 7 (N/A (not an
Applications track paper))
<br>
[Robotics track ONLY]: Balance of Robotics and Automated
Planning and Scheduling: 6 (N/A (not a Robotics track paper))
<br>
[Robotics Track ONLY]: Evaluation on physical
platforms/simulators: 6 (N/A (not a Robotics track paper))
<br>
[Robotics Track ONLY]: Significance of the contribution:
6 (N/A (not a Robotics track paper))
<br>
<br>
----------- Review -----------
<br>
The paper describes an approach for learning abstract
models and hierarchies for hierarchies of AMDPs. These
hierarchies are similar, if not exactly the same, as those used
by frameworks such as MAXQ, where each task in the hierarchy is
an MDP with actions corresponding to child tasks. Prior AMDP
work apparently uses hand-specified models of each task/AMDP,
which are directly used for planning. This paper extends that
work by learning the models of each task/AMDP. This is done
using RMAX at each task. There is not a discussion of
convergence guarantees of the approach. Apparently convergence
must occur in a bottom-up way. Experiments are shown in two
domains and with two hierarchies in one of the domains (Taxi).
The approach appears to learn more efficiently than a prior
approach R-MAXQ. The exact reasons for the increased efficiency
were not exactly clear based on my understanding from the paper.
<br>
<br>
The paper is well-written at a high level, but the more
technical and formal descriptions could be improved quite a bit.
For example, the key object AMDP, is only described informally
(the tuple is not described in detail). Most of the paper is
written quite informally. Another example is that Table 1 talks
about "max planner rollouts", but I didn't see where rollouts
are used anywhere in the algorithm description.
<br>
<br>
After reading the abstract and introduction, I expected
that a big part of the contribution would be about actually
learning the hierarchy. However, that does not seem to be the
case. Rather, an off-the-shelf approach is used to learn
hierarchies and then plugged into the proposed algorithm for
learning the models of tasks. Further, this is only tried for
one of the two experimental domains. The abstract and
introduction should be more clear about the contributions of the
paper.
<br>
<br>
Overall, I was unclear about what to learn from the
paper. The main contribution is apparently algorithm 1, which
uses R-MAX to learn the models of each AMPD in a given
hierarchy. Perhaps this is a novel algorithm, but it feels like
more of a baseline in the sense that it is the first thing that
one might try given the problem setup. I may not be appreciating
some type of complexity that makes this not be straightforward.
This baseline approach would have been more interesting if some
form of convergence result was provided, similar to what was
provided for R-MAXQ.
<br>
<br>
<br>
The experiments show that R-AMDP learns faster and is
more computationally efficient than R-MAXQ. I was unable to get
a good understanding for why this was the case. This is likely
due to the fact that I was not able to revisit the R-MAXQ
algorithm and it was not described in detail in this paper. The
authors do try to explain the reasons for the performance
improvement, but I was unable to follow exactly. My best guess
based on the discussion is that R-MAXQ does not try to exploit
the state abstraction provided for each task by the hierarchy
("R-MAXQ must compute a model over all possible future states in
a planning envelope after each action"). Is this the primary
reason or is there some other reason? Adding the ability to
exploit abstractions in R-MAXQ seems straightforward, though
maybe I'm missing something.
<br>
<br>
------------------------------------------------------
<br>
<br>
Best wishes,
<br>
Gabi Röger and Sven Koenig
<br>
ICAPS 2018 program chairs
<br>
<br>
<br>
_______________________________________________
<br>
Robot-learning mailing list
<br>
<a class="moz-txt-link-abbreviated" href="mailto:Robot-learning@cs.umbc.edu">Robot-learning@cs.umbc.edu</a>
<a class="moz-txt-link-rfc2396E" href="mailto:Robot-learning@cs.umbc.edu"><mailto:Robot-learning@cs.umbc.edu></a>
<br>
<a class="moz-txt-link-freetext" href="https://lists.cs.umbc.edu/mailman/listinfo/robot-learning">https://lists.cs.umbc.edu/mailman/listinfo/robot-learning</a>
<br>
<a class="moz-txt-link-rfc2396E" href="https://lists.cs.umbc.edu/mailman/listinfo/robot-learning"><https://lists.cs.umbc.edu/mailman/listinfo/robot-learning></a>
<br>
<br>
<br>
<br>
_______________________________________________
<br>
Robot-learning mailing list
<br>
<a class="moz-txt-link-abbreviated" href="mailto:Robot-learning@cs.umbc.edu">Robot-learning@cs.umbc.edu</a>
<a class="moz-txt-link-rfc2396E" href="mailto:Robot-learning@cs.umbc.edu"><mailto:Robot-learning@cs.umbc.edu></a>
<br>
<a class="moz-txt-link-freetext" href="https://lists.cs.umbc.edu/mailman/listinfo/robot-learning">https://lists.cs.umbc.edu/mailman/listinfo/robot-learning</a>
<br>
<a class="moz-txt-link-rfc2396E" href="https://lists.cs.umbc.edu/mailman/listinfo/robot-learning"><https://lists.cs.umbc.edu/mailman/listinfo/robot-learning></a>
<br>
<br>
<br>
<br>
<br>
_______________________________________________
<br>
Robot-learning mailing list
<br>
<a class="moz-txt-link-abbreviated" href="mailto:Robot-learning@cs.umbc.edu">Robot-learning@cs.umbc.edu</a>
<br>
<a class="moz-txt-link-freetext" href="https://lists.cs.umbc.edu/mailman/listinfo/robot-learning">https://lists.cs.umbc.edu/mailman/listinfo/robot-learning</a>
<br>
<br>
</blockquote>
<br>
_______________________________________________
<br>
Robot-learning mailing list
<br>
<a class="moz-txt-link-abbreviated" href="mailto:Robot-learning@cs.umbc.edu">Robot-learning@cs.umbc.edu</a>
<br>
<a class="moz-txt-link-freetext" href="https://lists.cs.umbc.edu/mailman/listinfo/robot-learning">https://lists.cs.umbc.edu/mailman/listinfo/robot-learning</a>
<br>
</blockquote>
<br>
<div class="moz-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="moz-txt-link-abbreviated" href="mailto:mariedj@umbc.edu">mariedj@umbc.edu</a>
<br>
Voice: 410-455-3967
<br>
Fax: 410-455-3559</div>
</body>
</html>