Multi-Objective Reinforcement Learning-based Approach for Pressurized Water Reactor Optimization

arXiv:2312.10194v3 Announce Type: replace
Abstract: A novel method, the Pareto Envelope Augmented with Reinforcement Learning (PEARL), has been developed to address the challenges posed by multi-objective problems, particularly in the field of engineering where the evaluation of candidate solutions can be time-consuming. PEARL distinguishes itself from traditional policy-based multi-objective Reinforcement Learning methods by learning a single policy, eliminating the need for multiple neural networks to independently solve simpler sub-problems. Several versions inspired from deep learning and evolutionary techniques have been …

abstract arxiv challenges cs.ce cs.lg engineering evaluation multi-objective novel optimization pareto policy reactor reinforcement reinforcement learning solutions type water