Untangling Braids with Multi-agent Q-Learning

TL;DR

This paper applies multi-agent reinforcement learning to the problem of untangling braids, demonstrating improved performance with training and generating complex tangled braid examples.

Contribution

It introduces a reinforcement learning framework for braid untangling using multi-agent systems interfaced with OpenAI Gym, a novel approach in this domain.

Findings

Training improves untangling performance

Agents can generate complex braid examples

Multi-agent setup effectively models braid manipulation

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.