Connectionists: CfP: Workshop on Lifelong Learning: A Reinforcement Learning Approach @ICML 2017

[Sarath Chandar]

Dear Colleagues,

We would like to invite you to submit extended abstracts of between 4-6
pages to our 'Lifelong Learning: A Reinforcement Learning Approach' ICML
2017 Workshop which will be held in Sydney, Australia on August 10, 2017.

IMPORTANT INFORMATION

************************************************

Website: http://rlabstraction2016.wix.com/icml-2017
<http://rlabstraction2016.wix.com/icml-2017>

Date: 10 August 2017

Location: Sydney, Australia

Submission deadline: 6th June 2017, 11:59 PM (GMT+2)

OVERVIEW

************************************************

One of the most challenging and open problems in Artificial Intelligence
(AI) is that of Lifelong Learning:

“Lifelong Learning is the continued learning of tasks, from one or more
domains, over the course of a lifetime, by a lifelong learning system. A
lifelong learning system efficiently and effectively (1) retains the
knowledge it has learned; (2) selectively transfers knowledge to learn new
tasks; and (3) ensures the effective and efficient interaction between (1)
and (2).”

Lifelong learning is still in its infancy. Many issues currently exist such
as learning general representations, catastrophic forgetting , efficient
knowledge retention mechanisms and hierarchical abstractions .  Much work
has been done in the Reinforcement Learning (RL) community to tackle
different elements of lifelong learning. Active research topics include
hierarchical abstractions, transfer learning, multi-task learning and
curriculum learning. With the emergence of powerful function approximators
such as in Deep Learning, we feel that now is a perfect time to provide a
forum to discuss ways to move forward and provide a truly general lifelong
learning framework, using RL-based algorithms, with more rigour than ever
before. This workshop will endeavour to promote interaction between
researchers working on the different elements of lifelong learning to try
and find a synergy between the various techniques.

SUBMISSION

************************************************

The submitted work should be an extended abstract of between 4-6 pages
(including references). The submission should be in pdf format and should
follow the style guidelines for ICML 2017. The review process is
double-blind and the work should be submitted by the latest 6th June 2017,
11:59 PM(GMT+2). Submissions must be made through easychair:
https://easychair.org/conferences/?conf=llicml2017

AREAS OF INTEREST

************************************************

   -

   Using Hierarchical Abstractions to perform lifelong learning (e.g.,
   skills/options and state space representations)
   -

   Transfer Learning
   -

   Multi-task Learning
   -

   Curriculum Learning
   -

   Deep Learning as a tool for performing lifelong learning
   -

   Determine new, challenging benchmark domains


For more info see our website <http://rlabstraction2016.wix.com/icml-2017>.

WORKSHOP ORGANIZERS

************************************************

Sarath Chandar - University of Montreal

Balaraman Ravindran - Indian Institute of Technology

Daniel J. Mankowitz - Technion Israel Institute of Technology

Tom Zahavy - Technion Israel Institute of Technology

Shie Mannor - Technion Israel Institute of Technology

We look forward to reviewing your submissions and hope to see you in Sydney!

Kind regards,

Sarath, Ravi, Daniel, Tom and Shie

Lifelong Learning: A Reinforcement Learning Approach Workshop organizers
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20170522/6ab471bc/attachment.html>