星的四种视角 ✧
FIND THE RIGHT VENUE

RLJ.

先看研究方向和推荐类别,再核对投稿要求、日期和历史数据。

← 全部渠道
01 / RESEARCH SCOPE

适合投稿的研究方向

强化学习理论、算法与实证研究

CCF 等级待核实CCF 国际目录 · 2026 年第七版

方向是对渠道定位的概括,具体范围、投稿轨道和截止日期请以当年官方征稿为准。

02 / VERIFIED RECORDS

历史统计与核验记录

统计按原始口径保留。官方报告值与按分子、分母计算的值分别展示,缺失数据记为未公布。

尚无已核验的历史统计

没有记录不代表录用率为零。可以继续查看下方官方来源。

03 / OFFICIAL SOURCES

要求、日期与来源

这些是来源页面的摘录。日期、要求和征稿轮次可能变化,请以相应官方页面为准。

rlj.org有可用记录
查看官方来源 ↗
最近尝试
2026/11/19 13:15
最近成功
2026/11/19 13:15

最近抓取的页面摘录

抓取时间:2026/11/19 13:15。尚未经过人工核验。

Reinforcement Learning Journal
Publication Agreement
Reinforcement Learning Journal (RLJ)
The Reinforcement Learning Journal (RLJ) is a quarterly peer-reviewed publication
focusing on reinforcement learning. RLJ is complemented by the
Reinforcement Learning Conference ( RLC ), an associated
event where researchers can present and elaborate on their findings that are
published in RLJ. It is important to note that RLJ is an independent, peer-reviewed
journal that serves as a primary source of scholarly articles, with the associated
meeting, RLC, enhancing the reach and impact of the research published within the
RLJ upholds the principles of open access, providing free online access to all its
publications under the Creative Commons Attribution (CC BY) license. Authors retain
copyright over their work, thus promoting the free exchange of ideas within the
scientific community. For more information, see the RLJ
Publication Agreement .
Submissions to RLJ are accepted on a rolling basis, publishing a new volume four
times a year. Authors interested in contributing are encouraged to review the detailed
submission guidelines—see Submissions for details.
Published papers are available under Papers , and the journal's editors
are listed on the Editorial Board page.
ISSN 2996-8577 (Online)
ISSN 2996-8569 (Print)
2024, Volumes 1–5 DOI: 10.5281/zenodo.13899776
2025, Volume 6 DOI: 10.5281/zenodo.21537949

投稿与要求 · 来源摘录

  • Papers
  • Submissions
  • Reinforcement Learning Journal (RLJ)
  • Reinforcement Learning Journal (RLJ) — The Reinforcement Learning Journal (RLJ) is a quarterly peer-reviewed publication focusing on reinforcement learning. RLJ is complemented by the Reinforcement Learning Conference ( RLC ), an associated event where researchers can present and elaborate on their findings that are published in RLJ. It is important to note that RLJ is an independent, peer-reviewed journal that serves as a primary source of scholarly articles, with the associated meeting, RLC, enhancing the reach and impact of the research published within the journal.
  • Reinforcement Learning Journal (RLJ) — RLJ upholds the principles of open access, providing free online access to all its publications under the Creative Commons Attribution (CC BY) license. Authors retain copyright over their work, thus promoting the free exchange of ideas within the scientific community. For more information, see the RLJ Publication Agreement .
  • Reinforcement Learning Journal (RLJ) — Submissions to RLJ are accepted on a rolling basis, publishing a new volume four times a year. Authors interested in contributing are encouraged to review the detailed submission guidelines—see Submissions for details.
  • Reinforcement Learning Journal (RLJ) — Published papers are available under Papers , and the journal's editors are listed on the Editorial Board page.
  • Reinforcement Learning Journal (RLJ) — ISSN 2996-8577 (Online)
  • Reinforcement Learning Journal (RLJ) — ISSN 2996-8569 (Print)
  • Reinforcement Learning Journal (RLJ) — 2024, Volumes 1–5 DOI: 10.5281/zenodo.13899776
  • Reinforcement Learning Journal (RLJ) — 2025, Volume 6 DOI: 10.5281/zenodo.21537949
rlj.org有可用记录
查看官方来源 ↗
最近尝试
2026/11/20 00:45
最近成功
2026/11/20 00:45

最近抓取的页面摘录

抓取时间:2026/11/20 00:45。尚未经过人工核验。

Authors Guide — Reinforcement Learning Journal
Publication Agreement
This guide covers how to prepare your manuscript file: formatting, page limits, the
cover page, and what to submit after acceptance. For scope, originality, disclosure and
the review process, see RLJ Submission Guidelines .
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 exceeding 8 pages are reserved for papers that cannot fully convey 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 files . Any submissions that violate the style guidelines
may be rejected without further review.
At RLJ, the first page of the PDF file should be a one-page cover page. In addition to
the title and abstract, the cover page must include a box clearly stating the paper's
Submissions will be judged primarily on the contributions claimed on their cover pages
and the evidence provided to support those claims. 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.
Additionally, contribution statements should be contextualized and clearly (and briefly)
state the state of the field before the submission. The work discussed in the
contextualization needs to be relevant to the submission.
Reviewers use the cover page as a rubric—see
Supporting Claims for what constitutes sufficient support
for a claimed contribution.
Supplementary Material
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 obliged
to examine the supplementary materials or any text beyond the main text. Therefore, any
results critical to your paper should be fully detailed in the main text.
Note: the main text ends when the references begin. Appendices before the references are
treated as part of the main text: subject to the 8–12 page limit, peer-reviewed, and may
contain content central to the paper's claims. Supplementary material after the references
is not part of the main text, has no page limit, is not necessarily reviewed, and should not
contain any claims or material central to the paper.
We recommend including all parts (main text, appendices, references, and supplementary
material) in a single PDF file.
Preparing the Final Version
Upon paper acceptance, authors will be asked to submit a final version of the paper
generated using the [accept] option in the style files. At this stage, only minor
revisions (e.g., correcting typographical errors) will be permitted. Along with the
final PDF, authors must also submit a publication form acknowledging the
rights granted to the journal—see
Style Files and Forms .
Copyright remains with the authors, who are free to share the final version of their
work. See Publication for the licensing terms.

投稿与要求 · 来源摘录

  • Papers
  • Submissions
  • Authors Guide
  • Reviewers Guide
  • Authors Guide — This guide covers how to prepare your manuscript file: formatting, page limits, the cover page, and what to submit after acceptance. For scope, originality, disclosure and the review process, see RLJ Submission Guidelines .
  • Authors Guide / Formatting Instructions — Formatting Instructions
  • Authors Guide / 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.
  • Authors Guide / Formatting Instructions — Main texts exceeding 8 pages are reserved for papers that cannot fully convey 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 Guide / Formatting Instructions — Authors should look at previously published RLJ papers for examples of expectations on writing quality and organization. You must use the provided style files . Any submissions that violate the style guidelines may be rejected without further review.
  • Authors Guide / Cover Page — Cover Page
  • Authors Guide / Cover Page — At RLJ, the first page of the PDF file should be a one-page cover page. In addition to the title and abstract, the cover page must include a box clearly stating the paper's main contributions.
  • Authors Guide / Cover Page — Submissions will be judged primarily on the contributions claimed on their cover pages and the evidence provided to support those claims. 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.
  • Authors Guide / Cover Page — Additionally, contribution statements should be contextualized and clearly (and briefly) state the state of the field before the submission. The work discussed in the contextualization needs to be relevant to the submission.
  • Authors Guide / Cover Page — Reviewers use the cover page as a rubric—see Supporting Claims for what constitutes sufficient support for a claimed contribution.
  • Authors Guide / Supplementary Material — Supplementary Material
  • Authors Guide / Supplementary Material — 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 obliged to examine the supplementary materials or any text beyond the main text. Therefore, any results critical to your paper should be fully detailed in the main text.
  • Authors Guide / Supplementary Material — Note: the main text ends when the references begin. Appendices before the references are treated as part of the main text: subject to the 8–12 page limit, peer-reviewed, and may contain content central to the paper's claims. Supplementary material after the references is not part of the main text, has no page limit, is not necessarily reviewed, and should not contain any claims or material central to the paper.
  • Authors Guide / Supplementary Material — We recommend including all parts (main text, appendices, references, and supplementary material) in a single PDF file.
  • Authors Guide / Preparing the Final Version — Preparing the Final Version
  • Authors Guide / Preparing the Final Version — Upon paper acceptance, authors will be asked to submit a final version of the paper generated using the [accept] option in the style files. At this stage, only minor revisions (e.g., correcting typographical errors) will be permitted. Along with the final PDF, authors must also submit a publication form acknowledging the rights granted to the journal—see Style Files and Forms .
  • Authors Guide / Preparing the Final Version — Copyright remains with the authors, who are free to share the final version of their work. See Publication for the licensing terms.
rlj.org有可用记录
查看官方来源 ↗
最近尝试
2026/11/20 02:15
最近成功
2026/11/20 02:15

最近抓取的页面摘录

抓取时间:2026/11/20 02:15。尚未经过人工核验。

Submissions — Reinforcement Learning Journal
Publication Agreement
RLJ Submission Guide
The RLJ peer review process prioritizes rigorous methodology over perceived importance, aiming to foster scholarly discussions on both well-established and emerging topics in RL.
Submission Procedure
RLJ accepts submissions through
OpenReview on a rolling basis, with a new volume
published four times a year. Papers intended for presentation at RLC must be accepted
by that year's RLC deadline.
A submission is a single anonymized PDF typeset with the RLJ style
files. See the Authors Guide for how to prepare one. Once your paper
is under review, do not upload a new PDF or change the supplementary material without
prior approval from the Editors; submissions modified without approval will be desk
We invite submissions presenting 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,
including agentic systems)
Hierarchical RL (e.g., skill discovery, hierarchical representations and
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
Foundations (e.g., showing relationships between methods, formalizations,
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 (e.g., reward learning from human data, human-in-the-loop
Imitation learning (e.g., learning from demonstrations, apprenticeship learning,
Neuroscience, cognitive science, and philosophical work targeting a computational
TODO: scope enquiries email address . -->
Submissions must be concise, complete, and polished. Manuscripts should be carefully
proofread and written with clarity and precision. Authors planning to submit to RLJ
should consult the RLJ Reviewers Guide , which describes expectations for
presentation quality and common issues that may hinder evaluation.
Note that these instructions call for the rejection of work with even minor errors in
the scientific process that prevent reviewers from properly assessing the paper's
claims (e.g., omitting the number of trials, using phrases that result in
over-claiming), even if these errors could be corrected by changing a few words.
Furthermore, rejection typically comes with a 6-month restriction from resubmitting.
We therefore strongly encourage you to carefully read the instructions for reviewers to
ensure that you are familiar with how your work will be evaluated. Submissions that do
not meet these standards may be returned without review.
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
Authors may publish substantially similar versions on arXiv.
Disclosure of Funding
Authors must disclose all sources of funding and any relationships or interests that
could reasonably be perceived as supporting or influencing the reported work. This
disclosure is not solely intended to ensure that publications are attributed to the
appropriate funding organizations; it is also an important part of maintaining
transparency for readers and enabling them to evaluate the work in its full context.
Accordingly, authors should report all grants, contracts, fellowships, gifts, or other
financial support that contributed to the research, as well as any competing interests,
including additional sources of income or financial relationships related to the
subject of the manuscript. Disclosures should cover support received or interests held
within the 18 months preceding submission .
The review process for RLJ 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.
The RLJ 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 use OpenReview for the review process. However, reviews and papers that are rejected
or withdrawn will not be made public.
This section summarizes how your submission will be handled. The
RLJ Reviewers Guide is the authoritative version, and it is public
precisely so that authors can read it. We strongly encourage you to do so before
Who reviews your paper
Every submission is evaluated by at least two reviewers, supervised by an Editor .
The two reviewers play deliberately different roles, and this differs notably from the
typical NeurIPS/ICLR/ICML process:
A Technical Reviewer produces what is essentially a
list of technical errors in the paper. There is no commentary on novelty,
significance, or impact. This is not an oversight; it is intentional.
A Senior Reviewer writes the type of review authors
traditionally expect, focused on whether claims are matched by evidence—which
includes technical correctness—and on how the work is situated in the literature.
Both are asked to work through your cover page contribution by contribution, stating
for each one what evidence was offered and whether it was sufficient.
The stated duration of each step is a goal, not a guarantee. If a stage runs long, the
Editor is expected to leave a comment in OpenReview with an updated timeline.
Editors-in-Chief desk reject or assign an Editor
Editor desk rejects or assigns a Senior and a Technical Reviewer
Reviewers write their reviews
Editor writes the meta-review and drafts the decision
Editors-in-Chief approve the decision
When the reviewing pipeline is over capacity, we prioritize the timely review of initial
Note that the review process may be delayed around holidays and certain events (such as RLC). In such cases, the email you receive when submitting will indicate the delay.
Reviewers recommend Accept, Revision, or Reject. The decision itself rests with the
Editor, and is one of two:
Accept as is : The paper is accepted in its current form; only minor changes are
required, to the point that no response to the Editor is needed.
Reject : The paper is not accepted in its current form. The meta-review states
which of the two resubmission terms below applies.
A rejection carries one of two resubmission terms:
The meta-review says
When you may resubmit
The work is not yet ready for publication
As soon as you have addressed every concern the Editor raised
The work does not meet the acceptance criteria, or requires significant changes
Where resubmission is invited, the sooner you resubmit, the more likely it is that some
of the same editors and reviewers can be secured for it.
Note that a failure to support a claim typically results in rejection with the 6-month
wait, rather than an invitation to resubmit. See
If you are invited to resubmit
The meta-review will state what needs to be addressed. Your resubmission should come
with a letter to the Editor discussing the primary concerns raised and how your
changes address them. You may disagree with a concern, and that disagreement should
still be discussed in the letter even if you chose not to change the manuscript.
The Editor may then accept or reject the paper immediately, consult the previous
reviewers, or initiate an entirely new review.
Papers may be desk rejected by the Editors-in-Chief or by the assigned Editor, on the
basis of issues identifiable in a short skim. There are two kinds, and the difference to
Typographical and formatting
Template violations, text spilling into margins, messy references, unreadable figures, multiple typos
Fix and resubmit immediately
Missing essential related work or baselines, vacuous theoretical statements, overclaiming with insufficient empirical evidence
6-month wait before resubmitting
See Desk Rejection Criteria and Process for the full criteria.
How papers are evaluated
Acceptance is based only on the submission , not on the potential of the paper with
further edits. A paper that requires even minor changes may be desk rejected or rejected
with an invitation to resubmit. The five acceptance criteria reviewers apply are set out
in How Papers are Evaluated .
Two consequences are worth stating plainly for authors. First, presentation alone can
sink a paper : if a submission needs a nontrivial editing pass, restructuring, notation
cleanup, figure redesign, or reference cleanup, it will not be accepted as is. Second,
RLJ deliberately avoids tastemaking : acceptance is not based on perceived impact, and
clearly scoped incremental work should be accepted. Reviewers are explicitly instructed
not to argue that your environments are too simple, that your method is not state of the
art, that your method is too simple, or that you should have compared against work
published in the last six months.
Use of Large Language Models (LLMs)
The use of LLMs and other writing tools is allowed in preparing 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
Note that senior reviewers are instructed to verify that all cited papers exist, that
the listed authors are correct, and that publication venues are accurately reported—generative
AI tools can introduce citation errors and fabricated references.
All papers are published open access under the Creative Commons Attribution (CC BY)
license. Copyright remains with the authors, who are free to share the final version of
Accepted papers require a final version prepared with the [accept] option in the style
files, together with a signed publication agreement—see
Preparing the Final Version .
This journal does not charge publication fees, and all articles are freely accessible

投稿与要求 · 来源摘录

  • Papers
  • Submissions
  • Authors Guide
  • Reviewers Guide
  • RLJ Submission Guide
  • RLJ Submission Guide — The RLJ peer review process prioritizes rigorous methodology over perceived importance, aiming to foster scholarly discussions on both well-established and emerging topics in RL.
  • RLJ Submission Guide / Submission Procedure — Submission Procedure
  • RLJ Submission Guide / Submission Procedure — RLJ accepts submissions through OpenReview on a rolling basis, with a new volume published four times a year. Papers intended for presentation at RLC must be accepted by that year's RLC deadline.
  • RLJ Submission Guide / Submission Procedure — A submission is a single anonymized PDF typeset with the RLJ style files. See the Authors Guide for how to prepare one. Once your paper is under review, do not upload a new PDF or change the supplementary material without prior approval from the Editors; submissions modified without approval will be desk rejected.
  • RLJ Submission Guide / Scope — Scope
  • RLJ Submission Guide / Scope — We invite submissions presenting original research of interest to the reinforcement learning community. For example, research on topics including, but not limited to:
  • RLJ Submission Guide / Scope — RL algorithms (e.g., new algorithms for existing settings and new settings, including agentic systems)
  • RLJ Submission Guide / Scope — Hierarchical RL (e.g., skill discovery, hierarchical representations and abstractions)
  • RLJ Submission Guide / Scope — Exploration (e.g., intrinsic motivation, curiosity-driven learning, exploration–exploitation tradeoff)
  • RLJ Submission Guide / Scope — Theoretical RL (e.g., complexity results, convergence analysis)
  • RLJ Submission Guide / Scope — Social and economic aspects (e.g., safety, fairness, interpretability, privacy, trustworthiness, human-AI interaction)
  • RLJ Submission Guide / Scope — Bandit algorithms (e.g., theoretical contributions, practical algorithms)
  • RLJ Submission Guide / Scope — Planning algorithms (e.g., decision-making under uncertainty, model-based approaches)
  • RLJ Submission Guide / Scope — Foundations (e.g., showing relationships between methods, formalizations, unifying theory, clarifying misconceptions in the literature)
  • RLJ Submission Guide / Scope — Evaluation (e.g., methodology, meta-studies, replicability, and validity)
  • RLJ Submission Guide / Scope — Benchmarks (e.g., specific RL challenges, real-world applications)
  • RLJ Submission Guide / Scope — Applied RL (e.g., medical, operations, traffic)
  • RLJ Submission Guide / Scope — Deep RL (e.g., analysis of the interplay between RL and deep learning models)
  • RLJ Submission Guide / Scope — Multi-agent RL (e.g., cooperative, competitive, self-play)

日期信息 · 来源摘录

  • RLJ Submission Guide / Submission Procedure — RLJ accepts submissions through OpenReview on a rolling basis, with a new volume published four times a year. Papers intended for presentation at RLC must be accepted by that year's RLC deadline.