Learning to Unknot

by   Sergei Gukov, et al.

We introduce natural language processing into the study of knot theory, as made natural by the braid word representation of knots. We study the UNKNOT problem of determining whether or not a given knot is the unknot. After describing an algorithm to randomly generate N-crossing braids and their knot closures and discussing the induced prior on the distribution of knots, we apply binary classification to the UNKNOT decision problem. We find that the Reformer and shared-QK Transformer network architectures outperform fully-connected networks, though all perform well. Perhaps surprisingly, we find that accuracy increases with the length of the braid word, and that the networks learn a direct correlation between the confidence of their predictions and the degree of the Jones polynomial. Finally, we utilize reinforcement learning (RL) to find sequences of Markov moves and braid relations that simplify knots and can identify unknots by explicitly giving the sequence of unknotting actions. Trust region policy optimization (TRPO) performs consistently well for a wide range of crossing numbers and thoroughly outperformed other RL algorithms and random walkers. Studying these actions, we find that braid relations are more useful in simplifying to the unknot than one of the Markov moves.


Reinforcement Learning as One Big Sequence Modeling Problem

Reinforcement learning (RL) is typically concerned with estimating singl...

Survey on reinforcement learning for language processing

In recent years some researchers have explored the use of reinforcement ...

Bridging the gap between learning and heuristic based pushing policies

Non-prehensile pushing actions have the potential to singulate a target ...

An application of neural networks to a problem in knot theory and group theory (untangling braids)

We report on our success on solving the problem of untangling braids up ...

Efficient Wasserstein Natural Gradients for Reinforcement Learning

A novel optimization approach is proposed for application to policy grad...

Extreme Q-Learning: MaxEnt RL without Entropy

Modern Deep Reinforcement Learning (RL) algorithms require estimates of ...

Please sign up or login with your details

Forgot password? Click here to reset