Reinforcement Feature Transformation for Polymer Property Performance Prediction

Polymer property performance prediction aims to forecast specific features or attributes of polymers, which has become an efficient ap- proach to measuring their performance. However, existing machine learning models face challenges in effectively learning polymer representations due to low-quality polymer datasets, which conse- quently impact their overall performance. This study focuses on improving polymer property performance prediction tasks by re- constructing an optimal and explainable descriptor representation space. Nevertheless, prior research such as feature engineering and representation learning can only partially solve this task since they are either labor-incentive or unexplainable. This raises two issues: 1) automatic transformation and 2) explainable enhancement. To tackle these issues, we propose our unique Traceable Group-wise Reinforcement Generation Perspective. Specifically, we redefine the reconstruction of the representation space into an interactive pro- cess, combining nested generation and selection. Generation creates meaningful descriptors, and selection eliminates redundancies to control descriptor sizes. Our approach employs cascading reinforce- ment learning with three Markov Decision Processes, automating descriptor and operation selection, and descriptor crossing. We utilize a group-wise generation strategy to explore and enhance reward signals for cascading agents. Ultimately, we conduct experi- ments to indicate the effectiveness of our proposed framework.