论文标题
神经网络在结理论和群体理论中的问题（毫无疑问的辫子）中的应用
An application of neural networks to a problem in knot theory and group theory (untangling braids)
论文作者
论文摘要
我们报告了我们在解决20号长度和宽度4的问题方面的成功问题。我们在增强学习的框架内使用馈送前馈神经网络来训练代理商以最小的移动数量选择ReideMeister Move to ReideMeister Move to Untange Braids。
We report on our success on solving the problem of untangling braids up to length 20 and width 4. We use feed-forward neural networks in the framework of reinforcement learning to train the agent to choose Reidemeister moves to untangle braids in the minimal number of moves.
