Reinforcement learning is a key paradigm for developing intelligent agents that operate in complex environments and interact with humans. However, researchers face the need to explain and interpret the decisions of these systems, especially when it comes to ensuring their alignment with societal value systems. This paper marks the initial stride in an ongoing research direction by applying an inductive logic programming methodology to explain the policy learned by an RL algorithm in the domain of autonomous driving, thus increasing the transparency of the ethical behaviour of agents.

Inductive Logic Programming for Transparent Alignment with Multiple Moral Values

Celeste Veronese
;
Daniele Meli;Filippo Bistaffa;Alessandro Farinelli;
2023-01-01

Abstract

Reinforcement learning is a key paradigm for developing intelligent agents that operate in complex environments and interact with humans. However, researchers face the need to explain and interpret the decisions of these systems, especially when it comes to ensuring their alignment with societal value systems. This paper marks the initial stride in an ongoing research direction by applying an inductive logic programming methodology to explain the policy learned by an RL algorithm in the domain of autonomous driving, thus increasing the transparency of the ethical behaviour of agents.
2023
Inductive logic programming
Answer set programming
Explainable AI
Ethical Decision Making
File in questo prodotto:
File Dimensione Formato  
short3.pdf

accesso aperto

Licenza: Creative commons
Dimensione 271.05 kB
Formato Adobe PDF
271.05 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11562/1120547
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact