Rules2Lab: from Prolog Knowledge-Base, to Learning Agents, to Norm Engineering

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper proposes a methodology, called Rules2Lab, that maps a Prolog knowledge base onto a Gymnasium environment. States, actions, and constraints are defined in Prolog, while temporal, computational, and sub-symbolic operations are delegated to Python. We demonstrate our approach through a case study on privacy vulnerabilities in a data marketplace. In our simulation, a reinforcement learning agent attempts to access sensitive data, with a privacy breach defined by the similarity between inferred and private data. Inductive logic programming is then used to engineer a new norm that prevents such breaches, demonstrating how a new rule can be seamlessly integrated into the knowledge base. Preliminary results highlight how a Gymnasium environment can be effectively combined with logic-based modeling and inference.

Original languageEnglish
Title of host publicationMulti-Agent Systems - 21st European Conference, EUMAS 2024, Proceedings
EditorsRem Collier, Vivek Nallur, Alessandro Ricci, Samuele Burattini, Andrea Omicini
PublisherSpringer Science and Business Media Deutschland GmbH
Pages274-282
Number of pages9
ISBN (Print)9783031939297
DOIs
Publication statusPublished - 1 Jan 2025
Event21st European Conference on Multi-Agent Systems, EUMAS 2024 - Dublin, Ireland
Duration: 26 Aug 202428 Aug 2024

Publication series

NameLecture Notes in Computer Science
Volume15685 LNAI
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference21st European Conference on Multi-Agent Systems, EUMAS 2024
Country/TerritoryIreland
CityDublin
Period26/08/2428/08/24

Keywords

  • inductive logic programming
  • multi-agent system
  • norms
  • reinforcement learning

Fingerprint

Dive into the research topics of 'Rules2Lab: from Prolog Knowledge-Base, to Learning Agents, to Norm Engineering'. Together they form a unique fingerprint.

Cite this