TY - GEN
T1 - Rules2Lab
T2 - 21st European Conference on Multi-Agent Systems, EUMAS 2024
AU - Fratrič, Peter
AU - Holzenberger, Nils
AU - Amariles, David Restrepo
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
PY - 2025/1/1
Y1 - 2025/1/1
N2 - 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.
AB - 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.
KW - inductive logic programming
KW - multi-agent system
KW - norms
KW - reinforcement learning
UR - https://www.scopus.com/pages/publications/105009319991
U2 - 10.1007/978-3-031-93930-3_16
DO - 10.1007/978-3-031-93930-3_16
M3 - Conference contribution
AN - SCOPUS:105009319991
SN - 9783031939297
T3 - Lecture Notes in Computer Science
SP - 274
EP - 282
BT - Multi-Agent Systems - 21st European Conference, EUMAS 2024, Proceedings
A2 - Collier, Rem
A2 - Nallur, Vivek
A2 - Ricci, Alessandro
A2 - Burattini, Samuele
A2 - Omicini, Andrea
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 26 August 2024 through 28 August 2024
ER -