Connectionists: NIPS 2017 Workshop Call for Papers -- Hierarchical Reinforcement Learning

[Roy Fox]

We invite all researchers to submit their manuscripts for review.

********************************************************************************
Hierarchical Reinforcement Learning Workshop
NIPS 2017
Saturday, December 9
Long Beach, CA, USA
https://sites.google.com/view/hrlnips2017
Please address questions to: hrlnips2017 at gmail.com
********************************************************************************

Reinforcement Learning (RL) has become a powerful tool for tackling complex
sequential decision-making problems as demonstrated in high-dimensional
robotics or game-playing domains. Nevertheless, modern RL methods have
considerable difficulties when facing sparse rewards, long planning
horizons, and more generally a scarcity of useful supervision signals.

Hierarchical Reinforcement Learning (HRL) is emerging as a key component
for finding spatio-temporal abstractions and behavioral patterns that can
guide the discovery of useful large-scale control architectures, both for
deep-network representations and for analytic and optimal-control methods.
HRL has the potential to accelerate planning and exploration by identifying
skills that can reliably reach desirable future states. It can abstract
away the details of low-level controllers to facilitate long-horizon
planning and meta-learning in a high-level feature space. Hierarchical
structures are modular and amenable to separation of training efforts,
reuse, and transfer. By imitating a core principle of human cognition,
hierarchies hold promise for interpretability and explainability.

There is a growing interest in HRL methods for structure discovery,
planning, and learning, as well as HRL systems for shared learning and
policy deployment. The goal of this workshop is to improve cohesion and
synergy among the research community and increase its impact by promoting
better understanding of the challenges and potential of HRL. This workshop
further aims to bring together researchers studying both theoretical and
practical aspects of HRL, for a joint presentation, discussion, and
evaluation of some of the numerous novel approaches to HRL developed in
recent years.


NOTE: The main NIPS 2017 conference is currently sold out. If you intend to
submit a paper, please register to the workshops as soon as possible.
Registrations can be cancelled before November 16, 2017, for a full refund.


IMPORTANT DATES:
- Submission deadline: Wednesday, November 1, 2017 (Anywhere on Earth)
- Author notification: Monday, November 13, 2017
- Final paper posted online: Monday, December 4, 2017
- Workshop: Saturday, December 9, 2017

SUBMISSION DETAILS:
- Research papers are solicited on Hierarchical Reinforcement Learning, its
theory and practice, and related fields (optimal control, cognitive
science, neuroscience, and others).
- Contributed papers may include novel research, preliminary results, or
surveys.
- Papers are limited to 4 pages, excluding references, in the latest
camera-ready NIPS style:
https://nips.cc/Conferences/2017/PaperInformation/StyleFiles
- Accepted papers will be made publicly available as a non-archival report,
allowing future submissions to archival conferences or journals.
- Please submit via CMT3: https://cmt3.research.microsoft.com/HRL2017
- Please check the workshop website for the latest updates:
https://sites.google.com/view/hrlnips2017

ACCEPTED PAPERS:
- All accepted papers will be presented as spotlights and during two poster
sessions.
- Authors of top accepted papers will be invited to give a short
contributed talk.
- Lead authors of outstanding papers will be invited to a lunchtime
discussion with the workshop’s invited speakers.
- Accepted student authors will be invited to apply for travel and
registration support.
- The best paper will win an award.

INVITED SPEAKERS:
Pieter Abbeel (OpenAI/UC Berkeley)
Matt Botvinick (DeepMind/UCL)
Jan Peters (TU Darmstadt)
Doina Precup (McGill)
David Silver (DeepMind/UCL)
Josh Tenenbaum (MIT)

ORGANIZERS:
Andrew Barto (UMass)
Doina Precup (McGill)
Shie Mannor (Technion)
Tom Schaul (DeepMind)
Roy Fox (UCB)
Carlos Florensa (UCB)
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20170919/6e4fdbe4/attachment.html>