A Normative Supervisor for Reinforcement Learning Agents
File version
Version of Record (VoR)
Author(s)
Bartocci, E
Ciabattoni, A
Governatori, G
Griffith University Author(s)
Primary Supervisor
Other Supervisors
Editor(s)
Date
Size
File type(s)
Location
Virtual
Abstract
We introduce a modular and transparent approach for augmenting the ability of reinforcement learning agents to comply with a given norm base. The normative supervisor module functions as both an event recorder and real-time compliance checker w.r.t. an external norm base. We have implemented this module with a theorem prover for defeasible deontic logic, in a reinforcement learning agent that we task with playing a “vegan” version of the arcade game Pac-Man.
Journal Title
Conference Title
28th International Conference on Automated Deduction Proceedings
Book Title
Edition
Volume
12699
Issue
Thesis Type
Degree Program
School
Publisher link
Patent number
Funder(s)
Grant identifier(s)
Rights Statement
Rights Statement
© The Author(s) 2021. This chapter is licensed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
Item Access Status
Note
Access the data
Related item(s)
Subject
Artificial intelligence
Information systems
Persistent link to this record
Citation
Neufeld, E; Bartocci, E; Ciabattoni, A; Governatori, G, A Normative Supervisor for Reinforcement Learning Agents, 28th International Conference on Automated Deduction Proceedings, 2021, 12699, pp. 565-576