Call for Ideas

Aiming to contribute to the recent series of open research initiatives within the machine learning community (for instance, one can take a look at the open problems from COLT, the ML Collective initiative, or on Twitter 1, 2), the workshop will feature a poster session devoted to presenting ideas for collaborations, positions, and open challenges. The papers should be related to bridging the gap between experimental and theoretical reinforcement learning (see Call for Papers for the range of topics) and should include:

• A clear definition of the problem/idea/position.
• The motivation for studying the problem/idea/position and why it is important for the machine learning community.
• The current state of the problem/idea/position.

The submitted papers can either be problems/ideas/positions novel to the community, or problems/ideas/positions already proposed in published works. Submitted papers will be reviewed by the program committee. All accepted papers will have a poster presentation. Please note that at least one author of each accepted paper must be available for the poster and/or oral presentation. There will be no proceedings.

Important dates

• Submission deadline: May 29th, 2024, AoE May 31th, 2024, AoE.
• Submission email: arlet.icml2024@gmail.com.
• Notification of acceptance: June 17th, 2024, AoE.
• Posters and camera ready: July 14th, 2024, AoE.

Submission instructions

The page limit is 4 pages (excluding references and the appendix). Submissions may include supplementary material, but reviewers are only required to read the first 4 pages. Submissions should use the template provided by the adapted NeurIPS 2024 style files. The title should start with “Open Problem:”, ”Idea:”, or ”Position:”. The reviewing process is double-blind, so the submissions should be anonymized and should not contain information that could identify the authors. Parallel submissions (to a journal, conference, workshop, or preprint repository) are allowed.