Abstract:
Automating molecular design using deep reinforcement learning (RL) holds the promise of accelerating the discovery of new chemical compounds. A limitation of existing approaches is that they work with molecular graphs and thus ignore the location of atoms in space, which restricts them to (1) generating single organic molecules and (2) heuristic reward functions. To address this, we present a novel RL formulation for molecular design in 3D space, thereby extending the class of molecules that can be built. Our reward function is directly based on fundamental physical properties such as the energy, which we approximate via fast quantum-chemical calculations. To enable progress towards designing molecules in 3D space, we introduce MolGym, an RL environment comprising several molecular design tasks alongside with baselines. In our experiments, we show that our agent can efficiently learn to solve these tasks from scratch by working in a translation and rotation invariant state-action space.
