Paperlane

no. 16 · Tuesday 17 November 2026

RL unknotter, hard unknots and unknotting number

Anne Dranowski, Yura Kabkov and Daniel Tubbenhauer

math.GT · v5 · 19 pp

Abstract

We train a reinforcement learning agent to simplify hard unknot diagrams and pair it with a learned crossing selector to search for short unknotting sequences. Three examples found by the agent lead to an infinite family of prime two-bridge knots of unknotting number three whose connected sums with the figure-eight knot also have unknotting number three, and fifteen new unknotting upper bounds were found on the set of prime knots up to 13 crossings.

comments
19 pages, many figures, comments welcome
fields
Geometric Topology
pdf ↗ page arXiv:2603.07955 ↗