Call for Papers.

Submission Deadline: September 15, 2019
The workshop welcomes both theoretical and applied research, in addition to novel data sets and evaluation protocols. Whilst the majority of the NeurIPS-related work in this area comes from Deep Reinforcement Learning, we will not limit the workshop to only such approaches. More specifically, we welcome papers that include (but are not limited to):

  • Novel algorithms and methods which are able to perform:
    • ​Transfer and meta-learning methods that aim to efficiently generalize from a subset of experienced tasks to unseen tasks which may be drawn from the same or a similar distribution as the earlier tasks.
    • Multi-task learning methods which aim to explore how agents can simultaneously learn multiple dissociable skills from a given task distribution.
    • ​Unsupervised skill discovery methods which aim to learn diverse behaviors without a specific reward signal.
    • Hierarchical learning methods that enable the composition of subgoals or subtasks with shared structure.
  • ​Novel environments, and associated baselines, that enable the study of transferable skills in RL. This may include procedurally generated environments, or environments specifically designed to test for skills which are not context-dependent.
  • Metrics and evaluation protocols that can standardize future research outputs around studying and measuring the development of task-independent skills within agents. 
  • ​We are also interested in any approaches involving learning or measuring transferable skills that may come from outside the AI community, especially when there are lessons or methodologies that could help facilitate exploration of the topic within AI. 

Important Dates
  • Submission deadline: September 15, 2019 at 23:59 AOE (Anywhere On Earth)
  • Acceptance notification: October 1, 2019
  • ​Camera ready submission: November 25, 2019
  • Workshop website finalized with bios, papers and other relevant info: November 27, 2019
  • ​Workshop Day: December 14th

Instructions to Authors
Submissions of technical papers can be up to 8 pages excluding references and appendices. Short or position papers of 2 to 4 pages are welcome. All papers must be submitted in PDF format, using the NeurIPS 2019 author kit. Papers will be peer-reviewed and selected for oral or poster presentations at the workshop. Attendance is open to all, and at least one author of each accepted submission must be present at the workshop.
​
Reviewing will be blind to the identities of the authors, meaning that your paper should not contain the names or affiliations of the authors. Any supplementary material should be added as appendix to the main paper (authors can only submit a single PDF file).

Papers can now be submitted on EasyChair
Questions related to papers submission can be sent to: lts19.workshop@gmail.com

As NeurIPS does not produce technical reports for its workshops, we will arrange for the publication and distribution of the accepted papers. More details will be provided as the submission deadline nears.

If you have expertise in the area and would like to join our program committee please get in touch at lts19.workshop@gmail.com