Submission Instructions

RLJ/RLC 2026 uses the OpenReview platform to handle paper submissions, the review process, and corresponding with authors. The link to OpenReview will be provided at a later date.

Submission Format

Submissions should be in the form of a single PDF file. This single PDF file should contain the body of the paper, appendices, references, and supplementary material. Note that appendices appear before the references, are subject to the page limit, and can contain content central to the claims of the paper. Note that supplementary materials appear after the references, have no page limits, are not necessarily peer reviewed, and should not contain any claims or material central to the paper.

Authors may optionally submit additional supplementary materials in the form of a .zip file. This can include software, videos, data, and even other PDF files (e.g., code documentation).

Style Files

The main PDF file should be created in LaTeX using the style files provided at this link.

See the contents of this template document for additional instructions regarding the preparation of this PDF file. Authors are not required to use Overleaf to prepare their submission. The LaTeX source for the template can be downloaded by clicking the “Menu” button in the top-right, and then the “Source” icon near the top of the menu that appears.

Other Notes

For additional information about the submission and review process (e.g., the 8–12 page limit), see the Call for Papers.

Note that the style files include the mandatory cover page. This page plays a crucial role in the review of submissions, establishing the contributions of the submission that should be supported in the text and verified during the review process. We encourage authors to devote significant time to this cover page, carefully scoping the claims. To help with this process, the Program Committee has provided the following example cover pages.

• Example 1: Policy Gradient Methods for Reinforcement Learning with Function Approximation
• Example 2: Human-level Control through Deep Reinforcement Learning

Note that although these examples list the original authors of the work to show what the cover pages for these works would look like if they appeared in RLJ/RLC, these were created by the RLJ/RLC Program Committee.