Automating molecular design using deep reinforcement learning (RL) has the potential to greatly accelerate the search for novel materials. Despite recent progress on leveraging graph representations to design molecules, such methods are fundamentally limited by the lack of three-dimensional (3D) information. In light of this, we propose a novel actor-critic architecture for 3D molecular design that can generate molecular structures unattainable with previous approaches. This is achieved by exploiting the symmetries of the design process through a rotationally covariant state-action representation based on a spherical harmonics series expansion. We demonstrate the benefits of our approach on several 3D molecular design tasks, where we find that building in such symmetries significantly improves generalization and the quality of generated molecules.
翻译:利用深强化学习(RL)自动化分子设计有可能大大加速寻找新材料。尽管最近在利用图形表示方式设计分子方面有所进展,但由于缺乏三维(3D)信息,这种方法基本上受到限制。有鉴于此,我们提议为三维(3D)分子设计建立一个新型的行动者-化学结构结构,这种结构可以产生与以往方法不相容的分子结构。这是通过在球形协调器系列扩展的基础上,通过循环地共变国家-行动表示方式来利用设计过程的对称。我们展示了我们在若干三维(3D)分子设计任务上的做法的好处,我们发现在这种对称中建构可以大大改进生成的分子的概括性和质量。