Materials Discovery with Extreme Properties via Reinforcement Learning-Guided Combinatorial Chemistry

arXiv:2303.11833v2 Announce Type: replace-cross
Abstract: The goal of most materials discovery is to discover materials that are superior to those currently known. Fundamentally, this is close to extrapolation, which is a weak point for most machine learning models that learn the probability distribution of data. Herein, we develop reinforcement learning-guided combinatorial chemistry, which is a rule-based molecular designer driven by trained policy for selecting subsequent molecular fragments to get a target molecule. Since our model has the potential to generate …

abstract arxiv chemistry cs.lg data discovery distribution learn machine machine learning machine learning models materials probability q-bio.bm reinforcement reinforcement learning type via