The downstream product transformation of lignin depolymerization is of great interest in the production of high-value aromatic chemicals. However, this transformation is often impeded by chemical oxidation under harsh reaction conditions. In this study, we demonstrate that hypohalites generated in situ by the vanadium-containing chloroperoxidase from Curvularia inaequalis (CiVCPO) can halogenate various electron-rich and electron-poor phenol and phenolic acid substrates. Specifically, CiVCPO enabled decarboxylative halogenation, deformylative halogenation, halogenation, and direct oxidation reactions. The versatile transformation routes for the valorization of phenolic compounds showed up to 99% conversion and 99% selectivity, with a turnover number of 60,700 and a turnover frequency of 60 s^-1 for CiVCPO. This study potentially expands the biocatalytic toolbox for lignin valorization.

Typically, a Reinforcement Learning (RL) algorithm focuses in learning a single deployable policy as the end product. Depending on the initialization methods and seed randomization, learning a single policy could possibly leads to convergence to different local optima across different runs, especially when the algorithm is sensitive to hyper-parameter tuning. Motivated by the capability of Generative Adversarial Networks (GANs) in learning complex data manifold, the adversarial training procedure could be utilized to learn a population of good-performing policies instead. We extend the teacher-student methodology observed in the Knowledge Distillation field in typical deep neural network prediction tasks to RL paradigm. Instead of learning a single compressed student network, an adversarially-trained generative model (hypernetwork) is learned to output network weights of a population of good-performing policy networks, representing a school of apprentices. Our proposed framework, named Teacher-Apprentices RL (TARL), is modular and could be used in conjunction with many existing RL algorithms. We illustrate the performance gain and improved robustness by combining TARL with various types of RL algorithms, including direct policy search Cross-Entropy Method, Q-learning, Actor-Critic, and policy gradient-based methods.