RLC/RLJ 2026 Call For Papers

The third Reinforcement Learning Conference (RLC) will be held in Montreal, Quebec, Canada, from August 15 to 18, 2026. RLC provides a venue where reinforcement learning researchers can interact and share their research in a more focused setting than typical large machine learning venues.

The Reinforcement Learning Journal (RLJ) is an annual peer-reviewed publication focusing on reinforcement learning. RLJ is complemented by RLC, an associated event where researchers can present and elaborate on their findings published in RLJ. This relationship between RLJ and RLC remains unchanged from the first RLJ/RLC. It is important to note that RLJ is an independent, peer-reviewed journal that serves as a primary source of scholarly articles. The associated meeting, RLC, enhances the reach and impact of the research published within the journal.

The RLJ/RLC peer review process prioritizes rigorous methodology over subjective perceived importance, aiming to foster scholarly discussions on both well-established and emerging topics in RL.

We invite submissions presenting new and original research of interest to the reinforcement learning community. For example, research on topics including, but not limited to:

• RL algorithms (e.g., new algorithms for existing settings and new settings)
• Hierarchical RL (e.g., skill discovery, hierarchical representations and abstractions)
• Exploration (e.g., intrinsic motivation, curiosity-driven learning, exploration-exploitation tradeoff)
• Theoretical RL (e.g., complexity results, convergence analysis)
• Social and economic aspects (e.g., safety, fairness, interpretability, privacy, trustworthiness, human-AI interaction)
• Bandit algorithms (e.g., theoretical contributions, practical algorithms)
• Planning algorithms (e.g., decision-making under uncertainty, model-based approaches)
• Foundations (e.g., showing relationships between methods, unifying theory, clarifying misconceptions in the literature)
• Evaluation (e.g., methodology, meta-studies, replicability, and validity)
• Benchmarks (e.g., specific RL challenges, real-world applications)
• Applied RL (e.g., medical, operations, traffic)
• Deep RL (e.g., analysis of the interplay between RL and deep learning models)
• Multi-agent RL (e.g., cooperative, competitive, self-play)
• RL from human feedback or verified reward (e.g., reward learning from human data, human-in-the-loop learning)
• Imitation Learning (e.g., learning from demonstrations, apprenticeship learning, inverse RL)
• Neuroscience and cognitive science work targeting a computational RL audience

We also welcome interdisciplinary or multidisciplinary research that does not neatly fit into existing categories but which has an RL audience. In case of any questions, please reach out to [email protected].

Authors must also submit a one-page cover page alongside the PDF file that will be included with the final publication. In addition to the title and abstract of the paper, the cover page must include a box clearly stating the paper's main contributions. The submissions will be judged mostly on the contributions claimed on their cover pages and the evidence provided to support them. Major contributions should not be claimed in the main text if they do not appear on the cover page. Overclaiming can lead to a submission being rejected, so it is important to have well-scoped contribution statements on the cover page. It is up to the area chair, senior area chair, and program committee to decide whether the contribution statements should be adjusted before acceptance. Authors might be asked to modify their statement of contributions during the reviewer discussion phase and upload the modified cover page separately. Additionally, in general, contribution statements should be contextualized, clearly (and briefly) stating the state of the field before the submission. The work discussed in the contextualization needs to be relevant to the submission. Two examples of potential cover pages of classical papers in the field are provided alongside the RLJ/RLC template and submission instructions (link).

Dates and Deadlines:

• Feb 17: Submission site will open by this date
• March 1: Abstract submission deadline (anywhere on earth)
• March 5: Submission deadline (anywhere on earth)
• March 5 - March 13: Paper bidding
• Mar 13: Finalize paper assignment
• Mar 27: Reviews due (2 weeks to review)
• Mar 27 - April 10 (2 weeks): [Review adjustment phase] AC asks reviewers to adjust their reviews if needed; AC assigns emergency reviewers as needed
• April 10 - Apr 17: Author response phase. Authors will have an opportunity to send a short rebuttal in response to the reviews. No new results can be added in this phase.
• April 17 - April 24th: Reviewer discussion phase (authors may be contacted with questions and requests to update contributions listed on the cover page)
• Apr 24: Meta-reviews from ACs due
• May 8: Decision notification
• July 18: Camera-ready paper due
• Aug 15 - Aug 18: Conference

Formatting Instructions:

All submissions should be in PDF format. All of the content before (but not including) the references is referred to as the “main text.” There is a recommended page limit of 8 pages and a strict page limit of 12 pages for the main text; authors should use their best judgment to edit the paper to ensure the content needed to understand the main parts of the method is included in the main text. The cover page does not count towards the 8–12 page limit. Main texts of length beyond 8 pages are reserved for papers that cannot fully communicate their core scientific contributions within 8 pages (e.g., for clear and thorough proofs or plots related to additional experimentation). Reviewers may penalize papers for unnecessary main text length above 8 pages, so authors are advised to minimize length while maintaining scientific rigor. Authors should look at previously published RLJ papers for examples of expectations on writing quality and organization. You must use the provided style file (link) and follow the submission instructions (link). Any submissions that violate the style guidelines may be rejected without further review.

You are welcome to include supplementary materials alongside your paper submission. These can include code, extra figures, and videos. It is crucial, however, that the main text stands on its own as a complete document. Please note that reviewers are not obligated to examine the supplementary materials or any text beyond the main text. Therefore, any results critical to your paper should be fully detailed within the main text itself.

Note: The main text ends when the references begin. Appendices before the references are viewed as part of the main text and are subject to the 8-12 page limit, are peer-reviewed, and can contain content central to the claims of the paper. The cover page does not count towards the page limit. The Supplementary Material that appears after the references is not part of the main text, has no page limits, is not necessarily reviewed, and should not contain any claims or material central to the paper. We recommend including all parts (cover page, main text, appendices, references, and supplementary material) in a single PDF file.

Review Criteria: All submissions will be evaluated by at least two reviewers, supervised by an area chair. The reviewers will evaluate the paper based on the following:

• Technical correctness. RLJ/RLC will hold papers to a high bar for technical correctness. Submissions will be evaluated based on their suitability for publication.
• Novelty. Submissions should represent original work and offer new contributions to the field of RL. Papers must not be a mere rephrasing or duplication of the authors' previous research, nor should they simply recapitulate existing knowledge without providing new insights.
• Clarity of contributions. Submissions should clearly delineate their contributions to the field, with a precise articulation of its novel aspects in the provided cover page. The merit of a paper is not based on the scale of advancement it provides; instead, the emphasis is on the clear and precise enumeration of the new developments it introduces.
• Support for claimed contributions. Submissions should provide solid empirical and/or theoretical backing for their stated contributions and claims.
• Clarity of presentation. Submissions should be well-crafted and coherently organized, demonstrating a polished and professional standard of academic writing. Confusing text, undefined mathematical symbols, and imprecise claims are valid reasons for rejection.
• Relevance to the RL community. Submissions should convey clearly the relevance of the work to the reinforcement learning community, broadly defined.

Review Process: We use OpenReview for the review pro

cess. However, reviews and rejected or withdrawn papers will not be made public.

Attendance: One author of each accepted paper must register for and attend the conference to present accepted papers as either a poster or talk. Exceptions to the attendance requirement may be made in extenuating circumstances (e.g., due to visa restrictions).

Use of Large Language Models (LLMs): The use of LLMs and other writing tools is allowed in the preparation of submissions. However, 1) all listed authors should correspond to humans, and 2) the authors are responsible for ensuring that the content of the paper is correct and original. The authors are responsible for ensuring that plagiarized text does not occur even if the LLM is the source of the text.

Double-blind reviewing: The review process for RLJ/RLC is double-blind. As such, authors are responsible for ensuring that their submissions do not contain any identifying information. This applies to any materials linked from the submission, such as code. Papers violating this double-blind policy may be rejected without further review.

Dual submissions: Authors should not submit papers that are substantially similar to versions that have been published, accepted for publication, or submitted in parallel to other conferences or journals. Any such submissions may be rejected or retracted after publication. Authors may submit substantially similar versions to workshops and may publish substantially similar versions on arXiv. Notably, dual-submission with RLDM is explicitly allowed.

Author response: After reviews have been entered in OpenReview, authors will have a brief period to view reviews and submit brief responses to clarify potential misconceptions about their work. Responses will be in plain text and should focus on clarifying their paper as currently written; additional results will not be taken into account in the final decision.

Author response to AC questions: After initial reviews have been entered in OpenReview, authors might be asked clarifying questions raised by the ACs; if so, they will have a chance to respond to them. Please note this is not a rebuttal, just allowing the reviews and AC to better understand the paper and author rebuttal.

Publication of accepted submissions: The accepted papers will be published in the Reinforcement Learning Journal (RLJ, link) under ISSN 2996-8577 (online) and ISSN 2996-8569 (print). All authors of accepted papers will be required to sign the RLJ publication agreement prior to publication. Instructions for completing and uploading this form will be provided to authors of accepted papers after acceptance notification, but the content of the form can be viewed here: link.

Simultaneous Work: While authors are expected to reference and discuss relevant related work, they are not expected to reference or discuss any work published within three months of the paper submission deadline.