Connectionists: Extended Deadline for Submissions (Oct 16) - NIPS Workshop on Planning with Information Constraints

[Pedro Ortega]

=======================================================

      CfP - EXTENDED DEADLINE: Oct 16, 2013

 Workshop on Planning with Information Constraints
      for Control, Reinforcement Learning,
     Comp. Neuroscience, Robotics and Games

     http://www.seas.upenn.edu/~ope/workshop/

   NIPS 2013, Lake Tahoe, Nevada, United States,
                 December 9, 2013

=======================================================

We have extended our deadline for contributions to
October 16, 2013. Submissions in PDF should be emailed
to

ope at seas.upenn.edu

with the subject line "NIPS 2013 Workshop Submission"
no later than October 16, 2013. Submissions should be
4-8 pages in NIPS format, with an extra page for
references if necessary. Authors of the selected
papers will be notified to present their
work through short talks or posters presentations.

** About **

How do you make decisions when there are way more
possibilities than you can analyze? How do you decide
under such information constraints?

Planning and decision-making with information constraints
is at the heart of adaptive control, reinforcement
learning, robotic path planning, experimental design,
active learning, computational neuroscience and games.
In most real-world problems, perfect planning is either
impossible (computational intractability, lack of
information, diminished control) or sometimes even
undesirable (distrust, risk sensitivity, level of
cooperation of the others). Recent developments have
shown that a *single method*, based on the free energy
functional borrowed from thermodynamics, provides a
principled way of designing systems with information
constraints that parallels Bayesian inference. This
single method -known in the literature under various
labels such as KL-control, path integral control,
linearly-solvable stochastic control, information-theoretic
bounded rationality- is proving itself very general
and powerful as a foundation for a novel class of
probabilistic planning problems.

** Organizers **

Bert J. Kappen
Naftali Tishby
Jan Peters
David H. Wolpert
Evangelos Theodorou
Pedro A. Ortega