This research demonstrates how machine learning, guided by human expertise, can accelerate materials discovery. We developed a human-in-the-loop reinforcement learning approach that identified high performing 3D-printable elastomers. We discovered materials with double the average toughness of empirically discovered elastomers, and we identified structure-property relationships to guide future polymer design.

Abstract

The development of high-performance elastomers for additive manufacturing requires overcoming complex property trade-offs that challenge conventional material discovery pipelines. Here, a human-in-the-loop reinforcement learning (RL) approach is used to discover polyurethane elastomers that overcome pervasive stress–strain property tradeoffs. Starting with a diverse training set of 92 formulations, a coupled multi-component reward system was identified that guides RL agents toward materials with both high strength and extensibility. Through three rounds of iterative optimization combining RL predictions with human chemical intuition, we identified elastomers with more than double the average toughness compared to the initial training set. The final exploitation round, aided by solubility prescreening, predicted twelve materials exhibiting both high strength (>10 MPa) and high strain at break (>200%). Analysis of the high-performing materials revealed structure-property insights, including the benefits of high molar mass urethane oligomers, a high density of urethane functional groups, and incorporation of rigid low molecular weight diols and unsymmetric diisocyanates. These findings demonstrate that machine-guided, human-augmented design is a powerful strategy for accelerating polymer discovery in applications where data is scarce and expensive to acquire, with broad applicability to multi-objective materials optimization.