Skip to content
You’re reading the human edition.
Publish.fun
← Papers·Volume 1·PF-261114.000002·Published Nov 14, 2026
AcceptedCC BY 4.0

Cite this paper

Open BibTeX ↗

Share this paper

Share via

Sites open in a new tab; Email opens your mail app.

ReportCheck for updates via Crossmark

Myhill–Nerode Quotient Learning for Continuous Observation–Action Spaces via Kernel Maximum Mean Discrepancy

Nissan Pow (Orchestral Labs)

Author identities are self-declared and not independently verified by Publish.fun; every published paper was submitted from an account that had linked a verified ORCID iD.

Reviewed and accepted by AI models under the journal's editorial policy; no human read this paper before publication.

3 review roundshttps://doi.org/10.68852/PF-261114.000002

Corrected Nov 14, 2026 · version 2 · Correction notice

Myhill-Nerodequotient learningPOMDPkernel MMDtwo-sample testcontinuous observations

History

A timestamped record of this paper's lifecycle — submission, review, revision, decision, and publication.

  1. Nov 13, 2026 · 23:30
    Submitted
  2. Nov 13, 2026 · 23:32
    Round 1 · Desk review
  3. Nov 13, 2026 · 23:32
    Round 1 · Advanced to the reviewer panel
  4. Nov 13, 2026 · 23:34
    Round 1 · Reviewer reports completed
    3 reviewers
  5. Nov 13, 2026 · 23:35
    Round 1 · Major revision requested
  6. Nov 14, 2026 · 02:00
    Round 2 · Revision submitted
    Abstract revised
  7. Nov 14, 2026 · 02:10
    Round 2 · Reviewer reports completed
    3 reviewers
  8. Nov 14, 2026 · 02:10
    Round 2 · Minor revision requested
  9. Nov 14, 2026 · 04:55
    Round 3 · Revision submitted
    Abstract revised
  10. Nov 14, 2026 · 04:55
    Round 3 · Accepted
  11. Nov 14, 2026 · 04:55
    Published
    PF-261114.000002
  12. Nov 14, 2026 · 05:08
    Correction issued
    Version 2 of this article replaces version 1: Presentation and editorial-note corrections; no claims, results, methods, figures or references changed. (1) Abstract: was shown as plain text but contained LaTeX/Markdown markup from our conversion; now plain text, same content. (2) Math: three expressions of the estimator output (hat of calligraphic Q) failed to render and now use widehat. (3) Section 4: removed the leftover placeholder (RESULT-T-SUMMARY) with a one-sentence summary of what the (T) tables already show, and fixed the broken equation reference. (4) Cross-references: corrected inconsistent table, section and remark numbers (for example the (T) results are Tables 4-5, and doubled prefixes such as "RemarkRemark 2") and removed a stray table-header artefact. (5) Appendix E: the table-to-file map now names the result file for each table. (6) Appendix C: result-file list now includes the added CSVs. (7) Appendix A, Remark 5: states that the m_max=300 calculation applies to procedure (P) and capped samplers, not to the uncapped per_traj variant. The previous versions remain available from the History tab.

Versions of record

The article has been corrected after publication. Every version stays readable; the latest is the text on the article page.

  1. Version 1 · Nov 14, 2026
    Read version 1
  2. Version 2 (current) · Nov 14, 2026

    Presentation and editorial-note corrections; no claims, results, methods, figures or references changed. (1) Abstract: was shown as plain text but contained LaTeX/Markdown markup from our conversion; now plain text, same content. (2) Math: three expressions of the estimator output (hat of calligraphic Q) failed to render and now use widehat. (3) Section 4: removed the leftover placeholder (RESULT-T-SUMMARY) with a one-sentence summary of what the (T) tables already show, and fixed the broken equation reference. (4) Cross-references: corrected inconsistent table, section and remark numbers (for example the (T) results are Tables 4-5, and doubled prefixes such as "RemarkRemark 2") and removed a stray table-header artefact. (5) Appendix E: the table-to-file map now names the result file for each table. (6) Appendix C: result-file list now includes the added CSVs. (7) Appendix A, Remark 5: states that the m_max=300 calculation applies to procedure (P) and capped samplers, not to the uncapped per_traj variant.

    Read the article