Leveraging Evolutionary Surrogate-Assisted Prescription in Multi-Objective Chlorination Control Systems

TL;DR

This paper proposes Evolutionary Surrogate-Assisted Prescription (ESP) for optimizing multi-objective chlorination control systems, aiming to improve real-world agent training in water treatment, with preliminary promising results.

Contribution

It introduces the novel ESP framework and demonstrates its potential in real-world water chlorination control through initial experiments.

Findings

Preliminary results show ESP's effectiveness in multi-objective optimization.

ESP has potential to enhance real-world agent training in water treatment.

Initial experiments indicate promising improvements over traditional methods.

Abstract

This short, written report introduces the idea of Evolutionary Surrogate-Assisted Prescription (ESP) and presents preliminary results on its potential use in training real-world agents as a part of the 1st AI for Drinking Water Chlorination Challenge at IJCAI-2025. This work was done by a team from Project Resilience, an organization interested in bridging AI to real-world problems.