Reinforcement learning algorithms for the Untangling of Braids

We use reinforcement learning algorithms (Q-Learning and Deep Q-Learning) to tackle the problem of untangling braidsand to compare the results of both algorithms. The idea is to use multi-agent (two competing players) based approachto tackle the problem of untangling braids. We interface the braid untangling problem with the OpenAI Gym envi-ronment, a widely used way of connecting agents to reinforcement learning problems. The results provide evidencethat the more we train the system, the better the untangling player gets for both approaches at untangling braids. Thecomparison of both approaches produces interesting results, where Q- learning performs better while dealing with braidsof shorter length, whereas DQN performs slightly better while dealing with braids of longer lengt