Reinforcement learning supercharges redox flow batteries

Yang Cao, Cher Tian Ser, Marta Skreta, Kjell Jorner, Nathanael Kusanda, Alán Aspuru-Guzik

Abstract: Designing viable molecular candidates is pivotal to devising low-cost and sustainable storage systems. A reinforcement learning framework has been developed that can identify stable candidates for redox flow batteries in the large search space of organic radicals.