Towards Abstraction in ASP with an Application on Reasoning about Agent Policies

TL;DR

This paper introduces an automatic abstraction method for ASP programs that reduces problem size while preserving structure, aiding in reasoning about agent policies in large state spaces.

Contribution

It presents a novel approach to abstract ASP programs automatically, specifically targeting large problem instances and agent policy reasoning.

Findings

Successfully abstracts ASP programs while maintaining structure.

Reduces problem size for large state spaces.

Enables reasoning about agent policies more efficiently.

Abstract

ASP programs are a convenient tool for problem solving, whereas with large problem instances the size of the state space can be prohibitive. We consider abstraction as a means of over-approximation and introduce a method to automatically abstract (possibly non-ground) ASP programs that preserves their structure, while reducing the size of the problem. One particular application case is the problem of defining declarative policies for reactive agents and reasoning about them, which we illustrate on examples.