Keywords: deep reinforcement learning, molecular design, covariant neural networks
Abstract: 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.
One-sentence Summary: Covariant actor-critic based on spherical harmonics that exploits symmetries to design molecules in 3D
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Code: [![github](/images/github_icon.svg) gncs/molgym](https://github.com/gncs/molgym)
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/arxiv:2011.12747/code)