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.
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.
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.
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.
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 > Mathematics, Statistics and Actuarial Science, School of |
SWORD Depositor: | Unnamed user with email elements@essex.ac.uk |
Depositing User: | Unnamed user with email elements@essex.ac.uk |
Date Deposited: | 25 Apr 2022 13:18 |
Last Modified: | 01 Nov 2024 02:37 |
URI: | http://repository.essex.ac.uk/id/eprint/32749 |
Available files
Filename: 2109.14502v1.pdf