Untangling Braids with Multi-agent Q-Learning
This is an incremental application of existing multi-agent Q-learning to a novel domain of braid untangling, with limited scope.
The paper tackled the problem of untangling braids using reinforcement learning with two competing agents, one for tangling and one for untangling, and found that increased training improved the untangling agent's performance while the tangling agent generated effective tangled examples.
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.