Dear Colleagues,

We would like to invite you to submit your work to the fourth Lifelong
Learning Workshop at ICML 2020, which will be held virtually (due to
COVID-19) on July 17/18, 2020.


*The deadline has been extended to 10th June 2020 to accommodate the
NeurIPS deadline extension.*



IMPORTANT INFORMATION

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

Website: <http://rlabstraction2016.wix.com/icml-2017>
https://lifelongml.github.io/

Date: 17 or 18 July 2020

Location: Virtual

Submission deadline: 10th June 2020, 11:59 PM Anywhere on Earth



KEYNOTE SPEAKERS

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

- Katja Hofmann (Microsoft Research)

- Irina Rish  (University of Montreal)

- Jurgen Schmiduber (IDSIA)

- Rich Sutton (University of Alberta)

- Partha Pratim Talukdar (Indian Institute of Science)



SUBMISSION

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

The submitted work should be between 4-8 pages (excluding references).
Recently published (or under-review) work is also welcome. The submission
should be in pdf format and should follow the style guidelines for ICML
2020 (found here
<https://media.icml.cc/Conferences/ICML2020/Styles/icml2020_style.zip>).
The review process is double-blind, and the work should be submitted by the
latest *10**th* June 2020, 11:59 PM (Anywhere on Earth). Submissions must
be made using OpenReview
<https://openreview.net/group?id=ICML.cc/2020/Workshop/LifelongML>.

There will be no formal publication of workshop proceedings. However, the
accepted papers will be made available online on the workshop website.

Best paper awards (a total of 2000$) will be given to the highest-quality
original submission(s) from students.

AREAS OF INTEREST

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

   -

   Catastrophic forgetting
   -

   Capacity expansion techniques
   -

   Modularity and Compositionality for lifelong learning
   -

   Transfer Learning
   -

   Multi-task Learning
   -

   Curriculum Learning
   -

   Meta-Learning
   -

   New architectures for lifelong learning
   -

   Determine new, challenging benchmark domains
   -

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

WORKSHOP ORGANIZERS

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

- Shagun Sodhani  (Facebook AI Research)

- Sarath Chandar (Polytechnique Montreal / Mila)

- Balaraman Ravindran (Indian Institute of Technology)

- Doina Precup (Mila / McGill University / DeepMind)



We look forward to reviewing your submissions!

Kind regards,

Shagun, Sarath, Ravi, Doina

Lifelong Learning Workshop organizers

(Contact: lifelon...@gmail.com)
_______________________________________________
uai mailing list
uai@engr.orst.edu
https://it.engineering.oregonstate.edu/mailman/listinfo/uai

Reply via email to