Evolutionary Surrogate-Assisted Prescription: Neuro-Symbolic Framework for Trustworthy Decisioning

Hormoz Shahrzad, Risto Miikkulainen

Keywords: Evolutionary Algorithms, Surrogate Modeling, Interpretable Machine Learning, Rule-Based Systems, Neuro-Symbolic AI, Decision Optimization, Trustworthy AI, Explainable AI

TL;DR: ESP turns data into trustworthy policies via a neural predictor and evolved interpretable rules, combining accuracy with transparency for safe, scalable decision-making.

Abstract:

Abundant records now link organizational contexts, actions, and
outcomes. Evolutionary Surrogate-Assisted Prescription (ESP) converts
such data into trustworthy policies through a two-stage
neuro-symbolic pipeline: a neural network Predictor surrogate is
trained first using supervised learning, after which an interpretable Prescriptor is
evolved against it using the EVOTER rule grammar. Decoupling
prediction from prescription yields high sample-efficiency, low
on-line risk, and explicit regularization, while the resulting rule
sets remain compact and auditable. Across diverse, safety-critical domains, ESP attains accuracy on par with—or exceeding—neural network models, yet retains full transparency, establishing a robust platform for large-scale, trustworthy decision optimization.

Track: Main Track

Paper Type: Industry Abstract

Resubmission: No

Submission Number: 91