Untangling Braids with Multi-agent Q-Learning
Machine Learning
2021-09-30 v1 Artificial Intelligence
Geometric Topology
Abstract
We use reinforcement learning to tackle the problem of untangling braids. We experiment with braids with 2 and 3 strands. Two competing players learn to tangle and untangle a braid. We interface the braid untangling problem with the OpenAI Gym environment, a widely used way of connecting agents to reinforcement learning problems. The results provide evidence that the more we train the system, the better the untangling player gets at untangling braids. At the same time, our tangling player produces good examples of tangled braids.
Keywords
Cite
@article{arxiv.2109.14502,
title = {Untangling Braids with Multi-agent Q-Learning},
author = {Abdullah Khan and Alexei Vernitski and Alexei Lisitsa},
journal= {arXiv preprint arXiv:2109.14502},
year = {2021}
}