Research

Paper

TESTING March 09, 2026

RL unknotter, hard unknots and unknotting number

Authors

Anne Dranowski, Yura Kabkov, Daniel Tubbenhauer

Abstract

We develop a reinforcement learning pipeline for simplifying knot diagrams. A trained agent learns move proposals and a value heuristic for navigating Reidemeister moves. The pipeline applies to arbitrary knots and links; we test it on ``very hard'' unknot diagrams and, using diagram inflation, on $4_1\#9_{10}$ where we recover the recently established and surprising upper bound of three for the unknotting number.

Metadata

arXiv ID: 2603.07955
Provider: ARXIV
Primary Category: math.GT
Published: 2026-03-09
Fetched: 2026-03-10 05:43

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.07955v1</id>\n    <title>RL unknotter, hard unknots and unknotting number</title>\n    <updated>2026-03-09T04:43:59Z</updated>\n    <link href='https://arxiv.org/abs/2603.07955v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.07955v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>We develop a reinforcement learning pipeline for simplifying knot diagrams. A trained agent learns move proposals and a value heuristic for navigating Reidemeister moves. The pipeline applies to arbitrary knots and links; we test it on ``very hard'' unknot diagrams and, using diagram inflation, on $4_1\\#9_{10}$ where we recover the recently established and surprising upper bound of three for the unknotting number.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='math.GT'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='stat.ML'/>\n    <published>2026-03-09T04:43:59Z</published>\n    <arxiv:comment>15 pages, many figures, comments welcome</arxiv:comment>\n    <arxiv:primary_category term='math.GT'/>\n    <author>\n      <name>Anne Dranowski</name>\n    </author>\n    <author>\n      <name>Yura Kabkov</name>\n    </author>\n    <author>\n      <name>Daniel Tubbenhauer</name>\n    </author>\n  </entry>"
}