A Review of Validation and Verification of Neural Network-based Policies for Sequential Decision Making

TL;DR

This paper surveys recent methods for validating and verifying neural network-based policies in sequential decision making, highlighting the growing research interest and diverse approaches to address new software quality challenges.

Contribution

It summarizes recent research contributions on NN policy verification and proposes future directions, filling a gap in understanding current validation techniques.

Findings

Increasing research interest in NN policy verification

Diverse techniques used for different verification problems

Growing number of studies from 2018 to 2023

Abstract

In sequential decision making, neural networks (NNs) are nowadays commonly used to represent and learn the agent's policy. This area of application has implied new software quality assessment challenges that traditional validation and verification practises are not able to handle. Subsequently, novel approaches have emerged to adapt those techniques to NN-based policies for sequential decision making. This survey paper aims at summarising these novel contributions and proposing future research directions. We conducted a literature review of recent research papers (from 2018 to beginning of 2023), whose topics cover aspects of the test or verification of NN-based policies. The selection has been enriched by a snowballing process from the previously selected papers, in order to relax the scope of the study and provide the reader with insight into similar verification challenges and their recent solutions. 18 papers have been finally selected. Our results show evidence of increasing interest for this subject. They highlight the diversity of both the exact problems considered and the techniques used to tackle them.