Research Repository

Untangling Braids with Multi-Agent Q-Learning

Khan, Abdullah and Vernitski, Alexei and Lisitsa, Alexei (2022) Untangling Braids with Multi-Agent Q-Learning. In: 2021 23rd International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC), 2021-12-07 - 2021-12-10, Timisoara, Romania.

2109.14502v1.pdf - Accepted Version

Download (336kB) | Preview


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.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: cs.LG; cs.AI; math.GT
Divisions: Faculty of Science and Health
Faculty of Science and Health > Mathematical Sciences, Department of
SWORD Depositor: Elements
Depositing User: Elements
Date Deposited: 25 Apr 2022 13:18
Last Modified: 23 Sep 2022 19:47

Actions (login required)

View Item View Item